INDEX

Explanations

sentences related to legal proceedings or imprisonment

oai_token-act-pair · gpt-3.5-turbo

references to prison sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

sie

-1.00

BLIC

-0.88

NetMessage

-0.72

chio

-0.72

aucus

-0.71

sonian

-0.71

rous

-0.70

endor

-0.69

aucuses

-0.67

sylv

-0.66

POSITIVE LOGITS

 sentences

1.11

 sentence

0.98

 probation

0.83

 imposed

0.83

 sentencing

0.82

ishment

0.78

 summ

0.77

 imprisonment

0.74

icts

0.74

 harshly

0.73

Activations Density 0.022%

sentences related to legal proceedings or imprisonment

references to prison sentences

No Comments

No Known Activations