INDEX

Explanations

mentions of surveys

oai_token-act-pair · gpt-3.5-turbo

references to surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.81

 slic

-0.76

speed

-0.72

vernment

-0.68

 rapp

-0.67

cream

-0.66

mph

-0.64

 chopping

-0.63

dry

-0.62

di

-0.62

POSITIVE LOGITS

 respondents

0.95

 respondent

0.94

 survey

0.90

 surveys

0.82

ors

0.80

naire

0.75

sylvania

0.74

 Bucks

0.72

ORS

0.72

 conducted

0.71

Activations Density 0.024%

mentions of surveys

references to surveys

No Comments

No Known Activations