INDEX

Explanations

references to data structures and their manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

thâu

-0.59

numerusform

-0.50

شهاد

-0.50

NameInMap

-0.48

isateur

-0.48

 Normdatei

-0.48

 ModelExpression

-0.47

haustible

-0.47

 Flow

-0.47

leyebilirsiniz

-0.47

POSITIVE LOGITS

append

0.94

extend

0.79

 append

0.75

 <<<<<<<<<<<<<<

0.74

 Extend

0.61

 extend

0.61

 Append

0.58

 extends

0.57

APPEND

0.56

Extend

0.55

Activations Density 0.141%

references to data structures and their manipulations

No Comments

No Known Activations