INDEX

Explanations

phrases related to negotiation and agreements

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to collective bargaining

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ocrates

-0.88

onso

-0.83

ocaly

-0.82

anti

-0.78

bish

-0.77

anamo

-0.77

eor

-0.77

opic

-0.76

oured

-0.76

icans

-0.76

POSITIVE LOGITS

 bargaining

1.12

 unions

0.88

 union

0.84

eering

0.84

 tong

0.78

 clauses

0.76

 agreements

0.76

 clout

0.73

 grievance

0.73

 negotiations

0.72

Activations Density 0.013%

phrases related to negotiation and agreements

terms and phrases related to collective bargaining

No Comments

No Known Activations