INDEX

Explanations

phrases related to law enforcement actions

oai_token-act-pair · gpt-3.5-turbo

references to arrest-related actions and entities

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

ĸļ

-0.86

bis

-0.80

eret

-0.77

iosis

-0.76

ibaba

-0.74

iversal

-0.69

wide

-0.66

closure

-0.66

chemy

-0.65

resy

-0.64

POSITIVE LOGITS

 perpetrators

1.02

 culprit

0.99

 entire

0.98

 innocent

0.91

 suspects

0.90

 perpetrator

0.90

guy

0.89

 dissidents

0.89

 victims

0.89

 murderer

0.89

Activations Density 0.437%

phrases related to law enforcement actions

references to arrest-related actions and entities

No Comments

No Known Activations