INDEX

Explanations

references to surveys

oai_token-act-pair · gpt-3.5-turbo

references to surveys and survey-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

burning

-0.75

speed

-0.69

vernment

-0.68

 slic

-0.66

 chopping

-0.65

gradation

-0.64

cream

-0.64

 reserves

-0.62

 rapp

-0.62

ntax

-0.62

POSITIVE LOGITS

 respondent

0.91

 respondents

0.90

 survey

0.86

ors

0.83

 conducted

0.78

 surveys

0.77

naire

0.74

sylvania

0.74

hower

0.73

ORS

0.72

Activations Density 0.023%

references to surveys

references to surveys and survey-related concepts

No Comments

No Known Activations