INDEX

Explanations

references to legal terminology and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

elfth

-0.58

enderror

-0.55

InjectAttribute

-0.53

 oeil

-0.52

 sauve

-0.51

inib

-0.51

 setOpen

-0.49

 heapq

-0.49

 Spisak

-0.49

falen

-0.48

POSITIVE LOGITS

脚注の使い方

0.63

 typelib

0.61

FunctionFlags

0.59

 Италијани

0.59

usercontent

0.56

hilt

0.55

@[

0.53

CPtr

0.53

 betweenstory

0.53

########.

0.50

Activations Density 0.779%

references to legal terminology and identifiers

No Comments

No Known Activations