INDEX

Explanations

specific words "Also" at a high activation level

oai_token-act-pair · gpt-3.5-turbo

references to articles or segments labeled "Also" indicating additional content or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

slot

-0.74

acious

-0.71

aciously

-0.65

jam

-0.64

agus

-0.63

$$$$

-0.63

 Canaver

-0.62

atics

-0.61

abies

-0.61

Â£

-0.61

POSITIVE LOGITS

 noteworthy

0.82

 Known

0.81

 included

0.78

 notor

0.78

 notable

0.75

 Called

0.74

 referred

0.73

onday

0.73

 includes

0.72

noon

0.72

Activations Density 0.047%

specific words "Also" at a high activation level

references to articles or segments labeled "Also" indicating additional content or information

No Comments

No Known Activations