INDEX

Explanations

phrases that provide reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Because" indicating explanations or justifications

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

shaw

-0.78

jet

-0.76

ns

-0.74

wn

-0.74

mint

-0.73

yan

-0.71

åĤ

-0.71

robe

-0.71

shr

-0.68

VR

-0.67

POSITIVE LOGITS

 fuck

0.70

 beware

0.69

 they

0.66

*/(

0.65

ecause

0.65

 Prosper

0.64

 there

0.64

âĶģ

0.64

olini

0.63

elligence

0.61

Activations Density 0.049%

phrases that provide reasons or explanations

instances of the word "Because" indicating explanations or justifications

No Comments

No Known Activations