INDEX

Explanations

proper nouns or phrases related to organizations or entities

oai_token-act-pair · gpt-3.5-turbo

specific names or important entities in the context of various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ĸļ

-0.57

[&

-0.56

 syll

-0.52

 thereof

-0.52

 guiActiveUnfocused

-0.52

*.

-0.51

EStreamFrame

-0.50

$.

-0.50

".

-0.50

 ....

-0.49

POSITIVE LOGITS

udos

0.71

 maintains

0.68

 spokesman

0.65

 retains

0.62

 acknowledges

0.60

 spokesperson

0.59

 accuses

0.59

 contends

0.59

 spokeswoman

0.59

 insists

0.58

Activations Density 1.106%

proper nouns or phrases related to organizations or entities

specific names or important entities in the context of various topics

No Comments

No Known Activations