INDEX

Explanations

technical terms and measurements related to experiments or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writeFieldEnd

-0.76

userdetails

-0.65

 EconPapers

-0.64

 Normdatei

-0.63

 resourceCulture

-0.63

nationality

-0.61

AndEndTag

-0.60

ChildScrollView

-0.57

seitige

-0.57

 كومونز

-0.57

POSITIVE LOGITS

 ſhall

0.54

tagHelper

0.52

SerializedName

0.52

 neceſſ

0.47

 ſhould

0.47

 ſaid

0.47

 reaſon

0.46

 purpoſe

0.46

legd

0.45

 Appear

0.45

Activations Density 0.145%

technical terms and measurements related to experiments or analyses

No Comments

No Known Activations