INDEX

Explanations

the word "fiction" or phrases related to fictional content

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fiction" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.74

hens

-0.71

hap

-0.67

baugh

-0.66

realDonaldTrump

-0.66

arov

-0.64

bred

-0.64

gars

-0.63

umm

-0.62

 Parenthood

-0.61

POSITIVE LOGITS

 fiction

1.00

 anthology

0.93

 Fiction

0.87

fiction

0.83

 novels

0.82

 Writers

0.82

 novelist

0.81

 writers

0.78

 writer

0.78

istically

0.77

Activations Density 0.022%

the word "fiction" or phrases related to fictional content

instances of the word "fiction" in various contexts

No Comments

No Known Activations