INDEX

Explanations

terms or phrases related to definitions or explanations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RectangleBorder

-0.75

RetentionPolicy

-0.74

twimg

-0.74

WireFormatLite

-0.73

 MainAxisSize

-0.73

PMailer

-0.71

ConstraintMaker

-0.70

 Exacts

-0.70

 ✔️

-0.69

 وتسجيلات

-0.68

POSITIVE LOGITS

 kasarigan

0.58

 sequence

0.58

 series

0.49

 cucchiai

0.47

 secuencia

0.46

 pattern

0.45

っていく

0.43

Un

0.42

fibonacci

0.42

series

0.41

Activations Density 1.079%

terms or phrases related to definitions or explanations

No Comments

No Known Activations