INDEX

Explanations

phrases related to specific names and entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

croft

-0.74

creen

-0.74

ships

-0.71

rising

-0.71

gow

-0.68

yy

-0.66

eer

-0.66

visors

-0.65

metics

-0.64

arity

-0.63

POSITIVE LOGITS

 Thib

1.07

 Babe

0.82

oland

0.77

âĵĺ

0.74

 Canaver

0.74

izont

0.73

 Spur

0.70

odka

0.70

pering

0.70

Dug

0.69

Activations Density 0.023%

phrases related to specific names and entities

proper nouns, particularly names of individuals and entities

No Comments

No Known Activations