INDEX

Explanations

phrases related to beginner experiences and learning processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

}>{

-0.59

ształ

-0.56

ざま

-0.51

 onBind

-0.48

UrlResolution

-0.47

reiche

-0.47

mappedBy

-0.47

aryen

-0.47

lois

-0.47

sny

-0.47

POSITIVE LOGITS

 novice

2.05

 newbie

1.97

 newbies

1.89

 novices

1.89

 inexperienced

1.87

 newcomer

1.84

 newcomers

1.83

 beginners

1.80

 beginner

1.80

 rookie

1.59

Activations Density 0.347%

phrases related to beginner experiences and learning processes in various contexts

No Comments

No Known Activations