INDEX

Explanations

content that includes specific programming or computational terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SourceChecksum

-0.56

кну

-0.49

TagMode

-0.48

 first

-0.48

 Ciencias

-0.44

anskrit

-0.44

ungsbedingungen

-0.42

άζ

-0.42

 kesi

-0.41

Stamina

-0.40

POSITIVE LOGITS

MigrationBuilder

0.88

</thead>

0.76

enderror

0.75

 <=",

0.72

Personendaten

0.69

 nakalista

0.68

 BoxFit

0.67

帖最后由

0.62

 فريبيس

0.60

 Chwiliwch

0.58

Activations Density 0.264%

content that includes specific programming or computational terminology

No Comments

No Known Activations