INDEX

Explanations

references to software or products and their enhancements or new additions

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the term "features" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cow

-0.71

 Metatron

-0.69

©¶æ¥µ

-0.66

doctor

-0.65

basketball

-0.64

assion

-0.64

<[

-0.62

onz

-0.61

OK

-0.61

gypt

-0.61

POSITIVE LOGITS

 features

3.74

 Features

2.77

features

2.65

 feature

2.51

Features

2.27

 Feature

1.97

feature

1.83

Feature

1.75

 functionality

1.51

eatures

1.48

Activations Density 0.019%

references to software or products and their enhancements or new additions

repeated mentions of the term "features" across various contexts

No Comments

No Known Activations