INDEX

Explanations

a specific type of word occuring before proper nouns or short phrases

oai_token-act-pair · gpt-3.5-turbo

instances of articles that indicate specific subjects or entities being introduced in a description

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

enance

-0.83

imentary

-0.75

aos

-0.74

encies

-0.72

anism

-0.69

SIGN

-0.68

eye

-0.67

Contents

-0.67

ophob

-0.65

advertisement

-0.65

POSITIVE LOGITS

 successor

0.93

 precursor

0.92

 remnant

0.86

 thinly

0.85

 small

0.85

 reference

0.85

hem

0.84

 longtime

0.84

 powerful

0.83

 member

0.82

Activations Density 0.138%

a specific type of word occuring before proper nouns or short phrases

instances of articles that indicate specific subjects or entities being introduced in a description

No Comments

No Known Activations