INDEX

Explanations

comments and documentation styles in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

enumi

-0.60

EndContext

-0.42

cèse

-0.41

 něm

-0.40

rippa

-0.40

</

-0.36

File

-0.35

sit

-0.35

POSITIVE LOGITS

 ProtoMessage

0.92

 betweenstory

0.81

SuspendLayout

0.77

BeginInit

0.66

 DBNull

0.65

errHandler

0.65

 nakalista

0.64

Amicalement

0.64

 насеље

0.63

TabIndex

0.62

Activations Density 0.162%

comments and documentation styles in code

No Comments

No Known Activations