INDEX

Explanations

the word "Murdoch."

oai_token-act-pair · gpt-3.5-turbo

references to significant figures associated with media ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

venge

-0.72

activated

-0.72

RNA

-0.72

errors

-0.71

eping

-0.70

ranged

-0.70

oxide

-0.68

graded

-0.64

othes

-0.63

aired

-0.63

POSITIVE LOGITS

 Murdoch

1.36

emouth

0.88

doms

0.84

mog

0.84

enthal

0.83

sonian

0.80

vertising

0.79

ificent

0.77

espie

0.77

rats

0.76

Activations Density 0.008%

the word "Murdoch."

references to significant figures associated with media ownership

No Comments

No Known Activations