INDEX

Explanations

references to Sarah Palin

oai_token-act-pair · gpt-3.5-turbo

mentions of Sarah Palin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

URI

-0.72

ires

-0.65

Ö¼

-0.63

reek

-0.62

Increases

-0.62

~~~~~~~~~~~~~~~~

-0.62

Oracle

-0.61

omething

-0.61

EAR

-0.60

REE

-0.60

POSITIVE LOGITS

 Palin

1.12

istani

0.86

igon

0.85

tera

0.80

EStream

0.80

bernatorial

0.79

aska

0.77

steen

0.77

ohydrate

0.75

 Schwarzenegger

0.74

Activations Density 0.008%

references to Sarah Palin

mentions of Sarah Palin

No Comments

No Known Activations