INDEX

Explanations

specific names, including proper nouns and abbreviations

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.37

 intersper

-1.10

 forbear

-0.76

 impelled

-0.76

 vainly

-0.75

 overcrow

-0.74

/**

-0.73

equila

-0.72

-0.71

 disbur

-0.70

POSITIVE LOGITS

 utop

0.81

 cioc

0.74

Tow

0.64

 Toxicol

0.63

tke

0.62

ToTensor

0.61

TO

0.60

 gmbh

0.60

 africain

0.60

 télévis

0.59

Activations Density 0.277%

specific names, including proper nouns and abbreviations

No Comments

No Known Activations