INDEX

Explanations

numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

texttt

-0.54

 تا

-0.54

až

-0.53

 jusqu

-0.50

getMenuInflater

-0.49

 ارش

-0.48

zus

-0.48

 hasta

-0.48

月から

-0.46

StringTo

-0.44

POSITIVE LOGITS

 inclusive

1.15

inclusive

1.06

 Inclusive

0.91

Inclusive

0.87

parsedMessage

0.81

CLUSIVE

0.79

 passim

0.75

 inclus

0.74

 Inclu

0.73

 inclu

0.73

Activations Density 0.501%

numerical data and statistical information

No Comments

No Known Activations