INDEX

Explanations

references to physical walls

oai_token-act-pair · gpt-3.5-turbo

references to physical walls

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

-0.79

amate

-0.68

CENT

-0.67

ptive

-0.67

lihood

-0.66

forward

-0.66

milo

-0.65

munition

-0.64

phrine

-0.62

×ķ

-0.62

POSITIVE LOGITS

papers

1.17

abies

1.14

aby

1.08

 wall

0.92

clock

0.89

 walls

0.89

top

0.85

 wart

0.84

tops

0.82

 thickness

0.82

Activations Density 0.012%

references to physical walls

references to physical walls

No Comments

No Known Activations