INDEX

Explanations

references to repeated processes or methods in a structured context

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

IntoConstraints

-0.40

ResponseWriter

-0.39

 integri

-0.38

Undefined

-0.36

CodedInputStream

-0.35

rizona

-0.35

 bour

-0.35

 axios

-0.34

 credi

-0.34

borderSide

-0.34

POSITIVE LOGITS

 EconPapers

0.58

 betweenstory

0.57

AutoScaleMode

0.55

 '\\;'

0.53

曖昧さ回避

0.52

 ModelRenderer

0.51

 مرئيه

0.49

HtmlAttribute

0.49

 noDo

0.49

 oprot

0.49

Activations Density 0.926%

references to repeated processes or methods in a structured context

No Comments

No Known Activations