INDEX

Explanations

sequences of characters or symbols in structured data or code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

RUnlock

-0.71

AndEndTag

-0.66

xus

-0.65

brium

-0.62

adaptiveStyles

-0.59

mybatisplus

-0.58

 Процитовано

-0.57

最快更新

-0.55

/>";

-0.55

ViewImports

-0.54

POSITIVE LOGITS

ParallelGroup

0.51

ftagPool

0.49

Ț

0.47

 AssemblyProduct

0.46

HasAnnotation

0.46

urnia

0.46

FormTagHelper

0.44

quelize

0.44

 liệu

0.43

omentos

0.43

Activations Density 0.047%

sequences of characters or symbols in structured data or code

No Comments

No Known Activations