INDEX

Explanations

phrases related to taking something into consideration or factoring it into a decision or judgment

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the importance of considering various factors or contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zai

-0.70

dot

-0.66

edly

-0.63

iants

-0.63

atile

-0.62

ians

-0.62

auld

-0.61

WARE

-0.60

 insulted

-0.59

owl

-0.59

POSITIVE LOGITS

 adulthood

0.76

displayText

0.72

 consideration

0.69

clusion

0.69

Merit

0.64

Putin

0.64

asons

0.63

 Clause

0.62

clusive

0.62

 account

0.62

Activations Density 0.039%

phrases related to taking something into consideration or factoring it into a decision or judgment

phrases that emphasize the importance of considering various factors or contexts

No Comments

No Known Activations