INDEX

Explanations

instances of the word "saw" occurring in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "saw"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 agric

-0.69

 mantle

-0.69

vernment

-0.68

xus

-0.65

currency

-0.64

 suscept

-0.63

onto

-0.63

ÃŃa

-0.61

cius

-0.60

inion

-0.60

POSITIVE LOGITS

dust

1.11

lights

0.93

awed

0.83

 firsthand

0.82

saw

0.79

lasses

0.77

yers

0.74

PsyNetMessage

0.72

Ĺ

0.71

tower

0.71

Activations Density 0.073%

instances of the word "saw" occurring in different contexts

instances of the word "saw"

No Comments

No Known Activations