INDEX

Explanations

words related to the concept of providing or seeking information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "inform" and its variations, indicating a focus on communication and information dissemination

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

ingu

-0.75

enf

-0.62

opes

-0.62

cdn

-0.62

oos

-0.62

imposed

-0.61

FUN

-0.61

cessive

-0.61

Pain

-0.60

hib

-0.60

POSITIVE LOGITS

ally

1.00

 inform

0.87

omic

0.82

acies

0.80

 informed

0.80

tale

0.75

ulty

0.74

isition

0.73

ingly

0.73

 incorpor

0.73

Activations Density 0.015%

words related to the concept of providing or seeking information

instances of the word "inform" and its variations, indicating a focus on communication and information dissemination

No Comments

No Known Activations