INDEX

Explanations

tags related to programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 <<<<<<<<<<<<<<

-0.72

انيف

-0.65

 judiciales

-0.59

 henvisninger

-0.58

 administrativos

-0.57

 sexuales

-0.55

kologie

-0.54

nologue

-0.53

 Reisedaten

-0.52

లాలు

-0.52

POSITIVE LOGITS

enumi

0.83

 Reſ

0.69

 كومونز

0.67

 Expl

0.66

 Skyl

0.66

 queſta

0.66

IBLIO

0.65

">${

0.64

 Dedu

0.64

="{{$

0.63

Activations Density 0.269%

tags related to programming or markup languages

No Comments

No Known Activations