INDEX

Explanations

references to 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.88

cream

-0.84

pires

-0.78

fired

-0.72

gran

-0.70

milo

-0.68

 derivative

-0.67

pire

-0.66

interstitial

-0.65

death

-0.65

POSITIVE LOGITS

 survey

1.05

 surveys

1.01

 respondent

0.95

 respondents

0.94

sylvania

0.88

 Surve

0.84

 Survey

0.81

ors

0.80

 surve

0.79

 poll

0.77

Activations Density 0.025%

references to surveys

references to surveys

No Comments

No Known Activations