INDEX

Explanations

terms related to authentication and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

bootstrapcdn

-0.61

RectangleBorder

-0.54

 '\\;'

-0.51

 defaultstate

-0.51

ety

-0.49

客様

-0.47

ugier

-0.44

 nessun

-0.44

ificação

-0.44

 poichè

-0.44

POSITIVE LOGITS

 się

0.85

 sobie

0.69

ся

0.63

 ModelExpression

0.63

się

0.61

сь

0.60

Chham

0.60

")));

0.60

afficheront

0.59

SourceChecksum

0.59

Activations Density 0.037%

terms related to authentication and verification processes

No Comments

No Known Activations