INDEX

Explanations

locations or place names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names or titles of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 exceptions

-0.74

 circuits

-0.65

 poles

-0.61

 nons

-0.61

 mainline

-0.60

 tracts

-0.60

 loopholes

-0.60

 certainty

-0.58

 necessities

-0.58

 criminals

-0.58

POSITIVE LOGITS

1.93

1.87

aan

1.59

1.56

eh

1.52

icz

1.50

iya

1.48

aq

1.47

oi

1.46

Activations Density 0.307%

locations or place names

proper nouns, specifically names or titles of people and places

No Comments

No Known Activations