INDEX

Explanations

references to measurements or comparisons in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

MigrationBuilder

-0.70

SerializedName

-0.69

Diweddarwch

-0.62

FormTagHelper

-0.59

EndContext

-0.57

UrlResolution

-0.57

mybatisplus

-0.55

PropertyChanging

-0.52

yntaxException

-0.52

kháu

-0.49

POSITIVE LOGITS

 third

3.77

 fourth

3.73

 fifth

3.62

 sixth

3.40

third

3.37

 seventh

3.31

fourth

3.17

 eighth

3.08

 ninth

3.06

fifth

3.05

Activations Density 0.945%

references to measurements or comparisons in data analysis

No Comments

No Known Activations