INDEX

Explanations

words formed by the capital letters in a specific pattern

oai_token-act-pair · gpt-3.5-turbo

the presence of promotional language and advertisement terminology

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

Gene

-0.72

Bug

-0.71

acus

-0.71

pmwiki

-0.69

itsch

-0.66

Cut

-0.65

Spring

-0.63

 Guilty

-0.63

Cent

-0.63

sbm

-0.63

POSITIVE LOGITS

xon

0.68

stood

0.64

 Âł Âł

0.63

 converter

0.62

ordinary

0.62

 stride

0.62

ŃĶ

0.62

FACE

0.62

illion

0.60

apeshifter

0.60

Activations Density 0.182%

words formed by the capital letters in a specific pattern

the presence of promotional language and advertisement terminology

No Comments

No Known Activations