INDEX

Explanations

specific words or phrases within sentences, such as names, locations, or legal terms

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their frequency in the document

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

adan

-0.65

abouts

-0.64

acons

-0.63

enos

-0.62

icide

-0.61

\/\/

-0.60

acy

-0.60

adra

-0.60

acre

-0.59

eca

-0.59

POSITIVE LOGITS

Scroll

1.13

PHOTOS

1.09

SPONSORED

0.93

RELATED

0.89

VIDEO

0.87

READ

0.85

ADVERTISEMENT

0.85

MORE

0.83

SEE

0.82

Sources

0.81

Activations Density 0.418%

specific words or phrases within sentences, such as names, locations, or legal terms

punctuation marks and their frequency in the document

No Comments

No Known Activations