INDEX

Explanations

notations or references related to numerical values and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 legales

-0.58

AppCompat

-0.56

GenerationType

-0.54

CJK

-0.52

PreAuthorize

-0.50

 remercier

-0.49

bufio

-0.49

Immutable

-0.46

indale

-0.46

bunch

-0.46

POSITIVE LOGITS

expandindo

0.80

ktop

0.59

Zer

0.58

Portale

0.55

חור

0.54

发表于

0.53

UpInside

0.53

 InputDecoration

0.52

tagHelperRunner

0.51

AutoScaleMode

0.50

Activations Density 0.475%

notations or references related to numerical values and variables

No Comments

No Known Activations