INDEX

Explanations

names of individuals associated with allegations or incidents marked by inappropriate physical contact

oai_token-act-pair · gpt-3.5-turbo

names and references related to allegations and accusations of inappropriate behavior

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

irtual

-0.74

istically

-0.72

OTS

-0.72

ODUCT

-0.70

 Sakuya

-0.69

IDE

-0.68

ATHER

-0.68

worldly

-0.68

ynt

-0.67

ISION

-0.67

POSITIVE LOGITS

heimer

1.27

 Franken

0.98

Ò

0.91

ste

0.85

berger

0.84

bourg

0.83

steen

0.82

fur

0.81

thal

0.81

furt

0.80

Activations Density 0.016%

names of individuals associated with allegations or incidents marked by inappropriate physical contact

names and references related to allegations and accusations of inappropriate behavior

No Comments

No Known Activations