INDEX

Explanations

phrases related to external and internal factors or attributes

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

RuleContext

-0.56

 CreateTagHelper

-0.55

WireFormatLite

-0.52

findpost

-0.52

rinho

-0.46

сы

-0.45

uxxxx

-0.44

 Hough

-0.43

Margins

-0.42

ة

-0.42

POSITIVE LOGITS

UserScript

0.78

 Extragalactic

0.56

MLLoader

0.56

 céramique

0.55

 secours

0.55

Lugares

0.54

getRuntime

0.52

shund

0.52

 precisione

0.51

GEBURTSDATUM

0.51

Activations Density 0.091%

phrases related to external and internal factors or attributes

No Comments

No Known Activations