INDEX

Explanations

phrases expressing extreme emotions or strong opinions

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

 alimentare

-0.50

Jeografia

-0.49

 jsPsych

-0.47

تب

-0.43

равда

-0.43

utilisons

-0.42

 entspre

-0.42

<bos>

-0.42

galus

-0.41

 ofrecerte

-0.41

POSITIVE LOGITS

脚注の使い方

0.89

zzleHttp

0.74

RenderAtEndOf

0.71

kloped

0.71

 mxArray

0.70

writeField

0.69

roek

0.69

 يتيمه

0.68

 jLabel

0.65

ScopeManager

0.64

Activations Density 0.145%

phrases expressing extreme emotions or strong opinions

No Comments

No Known Activations