INDEX

Explanations

references to the social media platform "Snapchat"

oai_token-act-pair · gpt-3.5-turbo

references to the social media platform Snapchat and its related features

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

ä

-0.81

@#&

-0.80

vernment

-0.73

ç·

-0.72

ĨĴ

-0.71

 GEAR

-0.67

RECT

-0.67

éĢ

-0.66

RAFT

-0.65

 Bermuda

-0.65

POSITIVE LOGITS

shots

1.15

shot

0.98

dragon

0.84

med

0.81

caster

0.80

ucket

0.79

arantine

0.78

deal

0.78

bucks

0.77

casters

0.76

Activations Density 0.016%

references to the social media platform "Snapchat"

references to the social media platform Snapchat and its related features

No Comments

No Known Activations