INDEX

Explanations

short phrases ending with specific punctuation

oai_token-act-pair · gpt-3.5-turbo

periods at the end of statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aband

-0.79

untarily

-0.75

 reven

-0.69

ittered

-0.67

ophy

-0.66

 occult

-0.65

ptin

-0.65

tones

-0.63

 dracon

-0.63

pse

-0.63

POSITIVE LOGITS

 Adds

1.10

<|endoftext|>

1.06

 Asked

0.97

[/

0.94

 âĢķ

0.93

↵

0.91

[/

0.89

 Related

0.85

 Ultimately

0.85

 Adding

0.85

Activations Density 0.076%

short phrases ending with specific punctuation

periods at the end of statements

No Comments

No Known Activations