INDEX

Explanations

proper nouns like names and titles

oai_token-act-pair · gpt-3.5-turbo

references to individuals with titles such as "Dr." or "Professor"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ü

-0.78

TPP

-0.75

album

-0.66

Netflix

-0.65

paren

-0.63

THIS

-0.62

 unden

-0.62

Tesla

-0.62

budget

-0.62

Film

-0.62

POSITIVE LOGITS

 Susan

0.82

 Said

0.80

 Lear

0.77

 Moran

0.77

 Chris

0.75

 Brian

0.75

 Richard

0.75

 Robert

0.74

 Geoffrey

0.74

 Erik

0.74

Activations Density 0.155%

proper nouns like names and titles

references to individuals with titles such as "Dr." or "Professor"

No Comments

No Known Activations