INDEX

Explanations

answer-related phrases or responses in a conversation

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

mathematical and programming expressions

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

IntoConstraints

-0.54

 AppCompatTheme

-0.52

밌

-0.44

fromnode

-0.44

 rates

-0.39

AnimationsModule

-0.39

bolts

-0.38

roc

-0.38

 varargin

-0.37

DateTimeField

-0.36

POSITIVE LOGITS

 ExecuteAsync

0.59

 ModelExpression

0.48

 fumée

0.45

BeginInit

0.45

bewerken

0.43

 ostavi

0.43

oneofs

0.42

 jScrollPane

0.42

 söyledi

0.42

 Catawiki

0.42

Activations Density 0.000%

answer-related phrases or responses in a conversation

mathematical and programming expressions

No Comments

No Known Activations