INDEX

Explanations

technical terms and error signals related to programming and system processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

})`

-0.38

$:

-0.38

|<\

-0.37

']))

-0.36

Fat

-0.35

má

-0.35

 gustado

-0.34

 Palabra

-0.34

 Gotta

-0.34

WHILE

-0.33

POSITIVE LOGITS

contentLoaded

0.61

########.

0.61

MigrationBuilder

0.59

ніципалі

0.59

 initComponents

0.57

complexContent

0.55

tagHelperRunner

0.54

 kasarigan

0.54

 informée

0.54

 Signalez

0.53

Activations Density 0.873%

technical terms and error signals related to programming and system processes

No Comments

No Known Activations