INDEX

Explanations

specific programming terms and code-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.53

-0.50

↵

-0.48

 kapcs

-0.46

 pienso

-0.46

 socialista

-0.46

 Amérique

-0.45

 judiciales

-0.44

 verschillen

-0.44

<eos>

-0.43

POSITIVE LOGITS

 MainAxisSize

1.09

 Roskov

0.96

Билгалдахарш

0.96

RenderAtEndOf

0.91

الحياه

0.90

rouvez

0.89

KURZBESCHREIBUNG

0.89

sizeCache

0.88

awtextra

0.87

WriteBarrier

0.86

Activations Density 0.005%

specific programming terms and code-related content

No Comments

No Known Activations