INDEX

Explanations

phrases related to labor strikes

oai_token-act-pair · gpt-3.5-turbo

terminology related to strikes and labor actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ophers

-0.86

iar

-0.80

afort

-0.78

indal

-0.75

eger

-0.75

 suspic

-0.75

opher

-0.74

ŀ

-0.74

thora

-0.73

glomer

-0.73

POSITIVE LOGITS

breakers

1.00

 strike

0.80

out

0.76

 zone

0.75

ters

0.74

breaker

0.73

 wages

0.72

force

0.71

 stopp

0.71

 unions

0.70

Activations Density 0.031%

phrases related to labor strikes

terminology related to strikes and labor actions

No Comments

No Known Activations