INDEX

Explanations

references to the word "Stone"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Stone."

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

merce

-0.90

olulu

-0.85

oresc

-0.82

orescence

-0.78

ornia

-0.78

unct

-0.72

ntil

-0.72

uates

-0.72

unal

-0.71

ership

-0.70

POSITIVE LOGITS

hill

0.97

works

0.93

falls

0.91

lings

0.88

hook

0.87

house

0.84

castle

0.84

Age

0.84

ring

0.83

 Cold

0.82

Activations Density 0.011%

references to the word "Stone"

mentions of the word "Stone."

No Comments

No Known Activations