INDEX

Explanations

places or objects within a specific radius

oai_token-act-pair · gpt-3.5-turbo

terms related to geographical measurements and specific institutions

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

aws

-0.77

ity

-0.74

ahoo

-0.70

inx

-0.70

anted

-0.70

anto

-0.66

ership

-0.65

 Devil

-0.64

inances

-0.64

abling

-0.64

POSITIVE LOGITS

bably

0.79

staking

0.75

thur

0.71

ãĤ¼ãĤ¦ãĤ¹

0.69

angular

0.67

 rall

0.67

ovember

0.66

 fries

0.66

zie

0.66

tery

0.66

Activations Density 0.060%

places or objects within a specific radius

terms related to geographical measurements and specific institutions

No Comments

No Known Activations