INDEX

Explanations

mentions of unemployment and related terms

oai_token-act-pair · gpt-3.5-turbo

references to unemployment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

afort

-0.82

roman

-0.80

ILE

-0.74

Zup

-0.74

eston

-0.72

sonian

-0.71

meric

-0.69

wcsstore

-0.69

agra

-0.69

×Ļ×

-0.69

POSITIVE LOGITS

 Unemployment

0.88

 unemployment

0.81

 compensation

0.77

 Compensation

0.75

 rate

0.75

 unemployed

0.74

 Insurance

0.71

 plag

0.70

 unemploy

0.69

 suicides

0.69

Activations Density 0.020%

mentions of unemployment and related terms

references to unemployment

No Comments

No Known Activations