INDEX

Explanations

mentions of fines and penalties

oai_token-act-pair · gpt-3.5-turbo

mentions of monetary penalties or fines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Ops

-0.83

 Sussex

-0.67

 Provider

-0.67

 Happ

-0.66

 Anon

-0.65

ãĥ¡

-0.64

OPS

-0.63

AMP

-0.63

 Piercing

-0.62

oscope

-0.61

POSITIVE LOGITS

alties

1.01

ky

0.82

hess

0.77

oshenko

0.75

 fines

0.75

alty

0.75

chy

0.74

chal

0.74

cling

0.73

cale

0.73

Activations Density 0.030%

mentions of fines and penalties

mentions of monetary penalties or fines

No Comments

No Known Activations