INDEX

Explanations

references to surveys

oai_token-act-pair · gpt-3.5-turbo

mentions of surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

burning

-0.70

 chopping

-0.67

iris

-0.66

 slic

-0.65

mph

-0.65

 reserves

-0.64

 curry

-0.62

vernment

-0.61

cream

-0.60

 marrow

-0.60

POSITIVE LOGITS

 respondents

0.97

 respondent

0.91

ors

0.90

 conducted

0.89

 survey

0.89

oral

0.83

naire

0.80

 surveys

0.79

stakes

0.77

 booths

0.75

Activations Density 0.033%

references to surveys

mentions of surveys

No Comments

No Known Activations