INDEX

Explanations

sources or attributions of information

oai_token-act-pair · gpt-3.5-turbo

references to sources or citations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arks

-0.75

 frogs

-0.72

ancies

-0.69

 impression

-0.68

eared

-0.68

 retard

-0.66

thal

-0.66

 frog

-0.65

 quiet

-0.64

 mornings

-0.63

POSITIVE LOGITS

via

1.20

Via

0.89

Via

0.85

rolet

0.81

 Brune

0.78

 Wikimedia

0.75

via

0.74

thia

0.72

LinkedIn

0.71

 PubMed

0.71

Activations Density 0.005%

sources or attributions of information

references to sources or citations

No Comments

No Known Activations