INDEX

Explanations

code-related syntax elements and structures

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

ing

-0.73

ة

-0.64

kreis

-0.58

 Mehl

-0.56

ffilm

-0.56

-0.55

ING

-0.54

lichting

-0.51

疱

-0.51

POSITIVE LOGITS

")->

1.32

 greateſt

1.03

 Monfieur

1.03

UIControlState

1.02

 Anſ

1.00

FetchType

0.98

enumii

0.97

 Majefty

0.97

SPJ

0.95

))->

0.94

Activations Density 0.058%

code-related syntax elements and structures

No Comments

No Known Activations