INDEX

Explanations

proper names related to politics, sports, and literary works

oai_token-act-pair · gpt-3.5-turbo

prominent names and references in the document

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

Negative Logits

tale

-0.72

AMI

-0.71

alling

-0.70

isconsin

-0.70

elsen

-0.69

ksh

-0.68

elf

-0.66

ki

-0.66

ALS

-0.66

agara

-0.65

POSITIVE LOGITS

mint

0.84

pool

0.79

 Kers

0.78

mont

0.75

inches

0.74

oner

0.73

xus

0.72

 Blossom

0.72

oqu

0.71

 Watts

0.70

Activations Density 0.084%

proper names related to politics, sports, and literary works

prominent names and references in the document

No Known Activations