INDEX

Explanations

references to previously discussed information or citations in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

rebro

-0.52

tez

-0.49

ೈ

-0.49

 bacterio

-0.49

claimers

-0.48

ateg

-0.47

 pict

-0.47

letch

-0.47

以

-0.47

Looking

-0.46

POSITIVE LOGITS

setupUi

0.79

synthesize

0.73

 nahilalakip

0.72

 doInBackground

0.71

enderror

0.70

évaluateur

0.70

addCriterion

0.68

 <<<<<<<<<<<<<<

0.67

 there

0.65

 ModelExpression

0.63

Activations Density 0.464%

references to previously discussed information or citations in a text

No Comments

No Known Activations