INDEX

Explanations

key phrases and terms related to biological processes and interactions

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

prepositions followed by words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ude

-0.42

anos

-0.41

öv

-0.41

nsk

-0.40

ori

-0.40

 stuff

-0.39

WireFormatLite

-0.39

TALL

-0.39

ibi

-0.39

lal

-0.39

POSITIVE LOGITS

ंदीखरीदारी

0.60

 חיצוניים

0.54

'},

0.52

 wikipagina

0.51

 typelib

0.50

 ſind

0.49

()]

0.48

KommentareTeilen

0.48

 الحره

0.47

{},

0.47

Activations Density 0.089%

key phrases and terms related to biological processes and interactions

prepositions followed by words

No Comments

No Known Activations