INDEX

Explanations

mentions of criminal charges or accusations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "charged" related to criminal activities

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

COR

-0.70

Wo

-0.70

estate

-0.69

perm

-0.69

DOM

-0.68

angular

-0.66

 livest

-0.66

>]

-0.65

toggle

-0.63

atomic

-0.62

POSITIVE LOGITS

heet

1.17

llah

1.08

eters

0.89

 criminally

0.87

 accused

0.80

 charges

0.80

 indicted

0.79

 charged

0.77

 indict

0.76

 accusing

0.73

Activations Density 0.024%

mentions of criminal charges or accusations

occurrences of the word "charged" related to criminal activities

No Comments

No Known Activations