INDEX

Explanations

instances of the word "See" in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "See"

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

 hurd

-0.72

 whistle

-0.69

atics

-0.68

 reckoned

-0.67

 nerv

-0.67

 ascert

-0.65

 susceptibility

-0.65

lied

-0.65

 tant

-0.65

ascal

-0.62

POSITIVE LOGITS

VERTIS

0.73

 whats

0.72

chin

0.68

iful

0.66

urat

0.65

ById

0.64

gments

0.63

efeated

0.63

igers

0.62

\/

0.61

Activations Density 0.015%

instances of the word "See" in the text

instances of the word "See"

No Comments

No Known Activations