INDEX

Explanations

words related to regulatory and immune responses

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

followed by -ulates, -iod, -ures, -resses, -ended, or -licating

np_acts-logits-general · gemini-2.0-flash

prefixes followed by specific suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 transfieras

-0.76

visiae

-0.75

észetes

-0.75

PerformLayout

-0.73

styrene

-0.68

rhosis

-0.68

propylene

-0.66

plasia

-0.64

AndroidJUnit

-0.64

 diſt

-0.64

POSITIVE LOGITS

 doInBackground

0.56

BindingResult

0.56

Slf

0.52

ArgsConstructor

0.49

NewUrlParser

0.48

 onPostExecute

0.47

DockStyle

0.46

 Nare

0.45

'>{

0.45

 nargin

0.44

Activations Density 0.804%

words related to regulatory and immune responses

followed by -ulates, -iod, -ures, -resses, -ended, or -licating

prefixes followed by specific suffixes

No Comments

No Known Activations