INDEX

Explanations

references to statues

oai_token-act-pair · gpt-3.5-turbo

mentions of statues

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

DN

-0.77

 Coastal

-0.73

avez

-0.72

Raw

-0.70

CE

-0.68

ricular

-0.65

comes

-0.65

actic

-0.64

ells

-0.63

 saline

-0.63

POSITIVE LOGITS

 statue

1.38

 statues

1.24

 sculpture

1.15

 sculptures

0.98

 Statue

0.95

 erected

0.92

 monument

0.86

 figur

0.83

 honoring

0.81

mage

0.81

Activations Density 0.012%

references to statues

mentions of statues

No Comments

No Known Activations