INDEX

Explanations

conversations involving questions and responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Cada

-0.59

 bağlantılar

-0.58

ParallelGroup

-0.56

깥

-0.56

 hoạch

-0.56

ypeł

-0.56

 recent

-0.55

writeValue

-0.55

TableHead

-0.55

ngrx

-0.53

POSITIVE LOGITS

 whereupon

1.14

 Darauf

0.89

 worauf

0.84

 Instantly

0.80

 thereupon

0.79

 aussitôt

0.78

 promptly

0.73

 immédiatement

0.73

 replied

0.72

 waarop

0.72

Activations Density 0.236%

conversations involving questions and responses

No Comments

No Known Activations