INDEX

Explanations

phrases related to legal penalties and fines

oai_token-act-pair · gpt-3.5-turbo

references to monetary penalties and fines

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

ãĤ¤ãĥĪ

-0.91

omorph

-0.79

omorphic

-0.75

natureconservancy

-0.73

ãĥ¡

-0.70

ierre

-0.70

ocaly

-0.67

Ops

-0.66

Psy

-0.66

ITNESS

-0.65

POSITIVE LOGITS

 levied

1.36

alties

1.04

 imposed

1.03

 incurred

0.93

 fines

0.90

 totaling

0.89

 owed

0.86

 penalties

0.85

 issued

0.84

 stemming

0.82

Activations Density 0.044%

phrases related to legal penalties and fines

references to monetary penalties and fines

No Comments

No Known Activations