INDEX

Explanations

phrases related to protests, strikes, and labor unrest

oai_token-act-pair · gpt-3.5-turbo

occurrences and contexts 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ophers

-0.84

hemy

-0.82

iar

-0.82

 Beir

-0.71

ŀ

-0.68

glomer

-0.67

 Leban

-0.67

afort

-0.66

 Bagg

-0.66

ħĭ

-0.66

POSITIVE LOGITS

breakers

1.02

force

0.92

out

0.84

 force

0.79

ters

0.76

 strike

0.75

 zone

0.73

fighters

0.73

outs

0.72

breaker

0.71

Activations Density 0.026%

phrases related to protests, strikes, and labor unrest

occurrences and contexts related to strikes and labor actions

No Comments

No Known Activations