INDEX

Explanations

the name "Leonard" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Leonard."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

skirts

-0.86

illance

-0.78

manship

-0.75

fare

-0.72

tch

-0.70

pron

-0.70

yrim

-0.69

dule

-0.69

eden

-0.69

Ã±

-0.65

POSITIVE LOGITS

 Leonard

1.13

 Lauder

0.91

 Cohen

0.86

ergic

0.82

wine

0.76

 Bernstein

0.75

ius

0.75

 Hayward

0.75

picking

0.73

zman

0.73

Activations Density 0.006%

the name "Leonard" in various contexts

mentions of the name "Leonard."

No Comments

No Known Activations