INDEX

Explanations

references to the word "Lincoln"

oai_token-act-pair · gpt-3.5-turbo

references to "Lincoln," specifically in various contexts and locations

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

 Flavoring

-0.76

NetMessage

-0.74

PDATE

-0.72

hift

-0.70

Org

-0.69

++++++++++++++++

-0.66

 exaggeration

-0.65

IAL

-0.64

ruct

-0.64

onent

-0.64

POSITIVE LOGITS

shire

1.71

hurst

0.84

 Memorial

0.80

incoln

0.79

dale

0.77

 Lincoln

0.77

 Parish

0.76

thal

0.74

ston

0.74

gren

0.74

Activations Density 0.039%

references to the word "Lincoln"

references to "Lincoln," specifically in various contexts and locations

No Comments

No Known Activations