INDEX

Explanations

words related to literary works, particularly novels

oai_token-act-pair · gpt-3.5-turbo

references to novels and literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

xon

-0.78

Downloadha

-0.78

tics

-0.65

henko

-0.64

older

-0.62

 impunity

-0.61

ardless

-0.60

poke

-0.59

Jr

-0.59

ĪĴ

-0.58

POSITIVE LOGITS

ties

1.28

izations

1.19

isations

1.05

ization

0.96

isation

0.95

istic

0.90

 manuscript

0.89

istically

0.85

culosis

0.84

ists

0.84

Activations Density 0.031%

words related to literary works, particularly novels

references to novels and literature

No Comments

No Known Activations