INDEX

Explanations

names of people, potentially researchers or authors

oai_token-act-pair · gpt-3.5-turbo

occurrences of proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Truman

-0.90

dit

-0.80

 Debor

-0.80

tur

-0.77

tor

-0.75

 Totem

-0.74

nces

-0.73

TD

-0.72

dt

-0.72

tyr

-0.71

POSITIVE LOGITS

berg

0.94

arn

0.89

 Goldberg

0.82

 Brooke

0.80

ãĥ¯

0.73

 iceberg

0.73

ong

0.71

 Live

0.70

burg

0.69

org

0.68

Activations Density 0.359%

names of people, potentially researchers or authors

occurrences of proper nouns and specific names

No Comments

No Known Activations