INDEX

Explanations

words associated with challenging authority or societal norms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dare" and its variations, often indicating challenges or confrontations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urgy

-0.74

ulator

-0.70

ulators

-0.69

effic

-0.68

 Rite

-0.67

iple

-0.65

utra

-0.65

ulatory

-0.64

OTOS

-0.62

Tool

-0.62

POSITIVE LOGITS

 dare

1.02

 Dare

0.96

 daring

0.89

 defy

0.86

ngth

0.83

evil

0.83

 dared

0.81

 roam

0.80

 boldly

0.75

 provoke

0.72

Activations Density 0.026%

words associated with challenging authority or societal norms

instances of the word "dare" and its variations, often indicating challenges or confrontations

No Comments

No Known Activations