INDEX

Explanations

occurrences of a specific character or symbol

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

terms related to legal and policy actions

oai_token-act-pair · gpt-3.5-turbo

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

 sacrific

-0.80

 ende

-0.76

 notor

-0.74

 imagination

-0.73

 puff

-0.73

 encyclopedia

-0.73

 federation

-0.71

 floppy

-0.71

 rune

-0.69

 outline

-0.69

POSITIVE LOGITS

Â¯

1.19

ï¸ı

1.07

âĢł

0.92

âĻ¦

0.89

ï¸

0.89

âģ

0.88

0.85

STEM

0.85

Â¶

0.83

âĢ¢âĢ¢

0.79

Activations Density 0.229%

occurrences of a specific character or symbol

terms related to legal and policy actions

No Comments

No Known Activations