INDEX

Explanations

terms related to fictional settings or elements

oai_token-act-pair · gpt-3.5-turbo

references to fictional elements and settings in narratives

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

Da

-0.76

hammad

-0.75

acks

-0.74

pour

-0.74

cake

-0.71

Ag

-0.70

wick

-0.69

artney

-0.69

erto

-0.69

nuts

-0.68

POSITIVE LOGITS

ized

1.10

ised

0.95

 universes

0.95

izations

0.95

izable

0.94

IZ

0.90

ization

0.89

isation

0.89

istically

0.87

arial

0.87

Activations Density 0.056%

terms related to fictional settings or elements

references to fictional elements and settings in narratives

No Comments

No Known Activations