INDEX

Explanations

references to toys

oai_token-act-pair · gpt-3.5-turbo

references to toys

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

xual

-0.74

idency

-0.71

ancock

-0.70

mary

-0.65

pard

-0.64

 sclerosis

-0.63

 Liberties

-0.62

icago

-0.62

 judgement

-0.61

clair

-0.61

POSITIVE LOGITS

 toys

1.03

toy

0.94

 Toys

0.92

 Crate

0.88

ota

0.85

slot

0.85

geon

0.85

Shop

0.82

haus

0.82

ulus

0.81

Activations Density 0.015%

references to toys

references to toys

No Comments

No Known Activations