INDEX

Explanations

phrases containing the word "true"

oai_token-act-pair · gpt-3.5-turbo

the word "True" and its variations in different contexts

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

acco

-0.82

served

-0.76

Corp

-0.76

ocene

-0.74

uled

-0.73

adish

-0.72

Pages

-0.71

artment

-0.70

anguage

-0.67

azine

-0.66

POSITIVE LOGITS

 believers

1.04

 believer

0.99

stic

0.79

 positives

0.77

 freshman

0.76

polit

0.76

çĭ

0.71

 intentions

0.70

 Detective

0.69

terday

0.68

Activations Density 0.025%

phrases containing the word "true"

the word "True" and its variations in different contexts

No Comments

No Known Activations