INDEX

Explanations

proper nouns, specifically related to books, authors, and media

oai_token-act-pair · gpt-3.5-turbo

references to specific names and terms related to media and fictional works

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pher

-0.87

onso

-0.81

grades

-0.79

oney

-0.76

frog

-0.76

ouse

-0.76

bestos

-0.73

hops

-0.71

onse

-0.70

ranged

-0.66

POSITIVE LOGITS

mire

0.86

 Predator

0.83

 Conan

0.81

agate

0.74

 precon

0.72

 Hannity

0.70

 Syndicate

0.70

Zin

0.69

aughs

0.69

 Carlson

0.68

Activations Density 0.027%

proper nouns, specifically related to books, authors, and media

references to specific names and terms related to media and fictional works

No Known Activations