INDEX

Explanations

words related to legal charges and criminal activities

oai_token-act-pair · gpt-3.5-turbo

counts of legal charges and offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 goodbye

-0.72

flush

-0.65

 congr

-0.65

fri

-0.65

opian

-0.64

ze

-0.64

Soft

-0.63

 valleys

-0.63

nas

-0.63

 Jagu

-0.61

POSITIVE LOGITS

 felony

1.51

 misdemeanor

1.47

 counts

1.47

 misdem

1.41

fel

1.22

 charges

1.19

 offenses

1.18

 count

1.13

 aggravated

1.11

 offences

1.09

Activations Density 0.122%

words related to legal charges and criminal activities

counts of legal charges and offenses

No Comments

No Known Activations