INDEX

Explanations

sequences of directional changes or transitions in processes or events

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

direction or sequence indicators

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

 CreateTagHelper

-0.57

AddTagHelper

-0.55

 esternos

-0.55

 &___

-0.51

Geplaatst

-0.50

 invokingState

-0.50

 ſche

-0.48

MessageTagHelper

-0.46

Numerade

-0.46

stdafx

-0.46

POSITIVE LOGITS

indd

0.42

帖最后由

0.42

 BoxDecoration

0.40

lapsingToolbar

0.38

eventually

0.38

 SwitchCompat

0.37

bootstrapcdn

0.37

itinéraire

0.37

 eventually

0.36

 kemudian

0.36

Activations Density 0.075%

sequences of directional changes or transitions in processes or events

direction or sequence indicators

No Comments

No Known Activations