INDEX

Explanations

words related to challenging or defying authority or societal norms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dare" in various contexts

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

urgy

-0.79

 Rite

-0.74

effic

-0.70

ulator

-0.69

iple

-0.68

ulatory

-0.67

ulators

-0.67

winner

-0.64

rator

-0.64

VERTISEMENT

-0.63

POSITIVE LOGITS

 dare

1.08

ngth

0.96

 Dare

0.93

 defy

0.88

 daring

0.87

 dared

0.84

 provoke

0.78

 boldly

0.77

 roam

0.75

 aspire

0.73

Activations Density 0.019%

words related to challenging or defying authority or societal norms

instances of the word "dare" in various contexts

No Comments

No Known Activations