INDEX

Explanations

technical terms and equipment related to software and hardware requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

bibfield

-0.59

iname

-0.53

 mxArray

-0.53

graphicx

-0.53

kiewicz

-0.51

ISHING

-0.51

vailability

-0.51

msgTypes

-0.49

Zep

-0.48

 valmist

-0.48

POSITIVE LOGITS

TextWatcher

0.72

 typelib

0.64

 Roskov

0.62

Билгалдахарш

0.61

 تعدى

0.59

LocationManager

0.59

writeFieldEnd

0.59

enumi

0.58

StructEnd

0.58

UnusedPrivate

0.57

Activations Density 1.239%

technical terms and equipment related to software and hardware requirements

No Comments

No Known Activations