INDEX

Explanations

references to academic journals and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

帖最后由

-0.54

zegor

-0.53

Hochspringen

-0.50

Efq

-0.50

diad

-0.50

 pinulongan

-0.49

 viri

-0.49

Kaynakça

-0.47

 Bann

-0.47

 chế

-0.47

POSITIVE LOGITS

GraphicsUnit

0.75

opacity

0.64

timeScale

0.62

argout

0.60

fraction

0.59

SetBool

0.59

WebControls

0.59

PhysRevLett

0.58

はじめに

0.57

 drôle

0.56

Activations Density 0.532%

references to academic journals and publication details

No Comments

No Known Activations