INDEX

Explanations

phrases related to coercion or manipulation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating coercion or manipulation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 corpus

-0.72

thora

-0.69

ghai

-0.65

ometimes

-0.64

terday

-0.63

etheless

-0.61

yip

-0.61

 capacitor

-0.61

hetically

-0.60

EMP

-0.59

POSITIVE LOGITS

 adulthood

0.93

 submission

0.89

jection

0.77

 Valhalla

0.76

ob

0.71

 adolescence

0.70

clusion

0.70

addon

0.67

 existence

0.66

 exile

0.65

Activations Density 0.056%

phrases related to coercion or manipulation

phrases indicating coercion or manipulation

No Comments

No Known Activations