INDEX

Explanations

words related to allegations and instances of sexual misconduct

oai_token-act-pair · gpt-3.5-turbo

terms related to sexual misconduct and allegations against individuals

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

REE

-0.84

 guiActiveUnfocused

-0.78

rious

-0.75

eric

-0.75

AY

-0.72

OTAL

-0.72

OTS

-0.71

ernel

-0.71

HCR

-0.70

ROM

-0.70

POSITIVE LOGITS

 accuser

1.30

 allegations

1.23

 allegation

1.05

Sexual

1.00

 abuser

0.97

 accusations

0.96

 abusers

0.95

 sexually

0.95

 complainant

0.94

 rape

0.91

Activations Density 0.128%

words related to allegations and instances of sexual misconduct

terms related to sexual misconduct and allegations against individuals

No Comments

No Known Activations