INDEX

Explanations

proper nouns related to political figures and locations

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Hammond" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uary

-0.69

Magikarp

-0.69

culosis

-0.68

 Leone

-0.65

gio

-0.60

ctory

-0.60

HIV

-0.59

ystem

-0.59

ozo

-0.59

 Surviv

-0.58

POSITIVE LOGITS

 Hammond

1.17

monds

0.99

sburg

0.97

shire

0.83

elin

0.81

arious

0.80

ilton

0.74

bean

0.73

ajo

0.72

mond

0.71

Activations Density 0.008%

proper nouns related to political figures and locations

mentions of the name "Hammond" in various contexts

No Comments

No Known Activations