INDEX

Explanations

references to writers

oai_token-act-pair · gpt-3.5-turbo

references to writers and writing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illon

-0.83

rals

-0.77

 CCTV

-0.77

Ĥª

-0.75

Ĭ±

-0.68

 Lumpur

-0.66

Sensor

-0.66

EGA

-0.66

avior

-0.64

hens

-0.63

POSITIVE LOGITS

writing

0.99

 laureate

0.98

writer

0.91

writers

0.87

uscript

0.86

writ

0.86

hip

0.84

 Beware

0.81

 fiction

0.78

smanship

0.76

Activations Density 0.076%

references to writers

references to writers and writing

No Comments

No Known Activations