INDEX

Explanations

instances of surprise or disbelief

oai_token-act-pair · gpt-3.5-turbo

the word "by" in various contexts, indicating reactions or evaluations

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

•layer 5 - surprise

No Comments

Negative Logits

ayne

-0.74

Runner

-0.74

Reviewed

-0.74

 ILCS

-0.74

aunder

-0.73

interrupted

-0.68

redits

-0.68

 largeDownload

-0.68

heit

-0.68

 teasp

-0.68

POSITIVE LOGITS

products

0.97

product

0.72

 Sapp

0.71

 virtue

0.70

 what

0.68

0.66

 seeing

0.65

 Rampage

0.65

how

0.64

 Heavenly

0.62

Activations Density 0.076%

instances of surprise or disbelief

the word "by" in various contexts, indicating reactions or evaluations

No Comments

No Known Activations