INDEX

Explanations

commands related to form submission or re-entering information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "enter"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

illard

-0.81

axter

-0.75

hovah

-0.72

 disadvant

-0.72

 tremend

-0.68

 polic

-0.68

 murd

-0.65

atility

-0.65

etimes

-0.65

 coun

-0.64

POSITIVE LOGITS

prise

1.73

prises

1.52

tainment

1.11

TAIN

0.93

taining

0.93

prising

0.91

igmatic

0.87

itus

0.83

tain

0.80

enter

0.80

Activations Density 0.007%

commands related to form submission or re-entering information

occurrences of the word "enter"

No Comments

No Known Activations