INDEX

Explanations

phrases including names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ional

-1.08

ivity

-0.86

=-=-=-=-=-=-=-=-

-0.77

abad

-0.73

 IMAGES

-0.71

ariat

-0.68

icks

-0.68

antly

-0.67

ioned

-0.67

iency

-0.65

POSITIVE LOGITS

Mae

1.08

emonic

0.98

zie

0.89

zza

0.80

ovember

0.78

zn

0.76

hl

0.75

vana

0.73

astern

0.73

pling

0.73

Activations Density 0.007%

phrases including names

references to specific individuals and names

No Comments

No Known Activations