INDEX

Explanations

references to classes and models in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

uesia

-0.60

OPTION

-0.55

 Optionen

-0.53

alingen

-0.53

CopyWith

-0.53

tingu

-0.52

EndContext

-0.52

rsiniz

-0.52

alinga

-0.52

 дух

-0.51

POSITIVE LOGITS

AlterField

0.94

 дописавши

0.90

 виправивши

0.90

parsedMessage

0.78

पया

0.77

AccessorTable

0.71

PerformLayout

0.68

 HasFactory

0.66

+#+#

0.66

rungsseite

0.64

Activations Density 0.014%

references to classes and models in a programming context

No Comments

No Known Activations