INDEX

Explanations

references to cynicism or cynically used language

oai_token-act-pair · gpt-3.5-turbo

terms associated with cynicism and its variations

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

acid

-0.73

 presses

-0.67

 challeng

-0.63

guards

-0.61

Grant

-0.61

aceous

-0.59

velength

-0.59

dated

-0.58

icides

-0.58

Franc

-0.57

POSITIVE LOGITS

Ö¼

1.04

aneers

0.98

obyl

0.89

sonian

0.87

osure

0.87

ulhu

0.83

blers

0.80

rolet

0.79

abal

0.77

Ñı

0.77

Activations Density 0.042%

references to cynicism or cynically used language

terms associated with cynicism and its variations

No Comments

No Known Activations