INDEX

Explanations

numeric representations, particularly those related to array sizes and indexing

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

code tags and punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 MainAxisSize

-0.60

 BoxDecoration

-0.58

matchCondition

-0.57

endphp

-0.56

fjspx

-0.53

DockStyle

-0.51

twimg

-0.45

CloseOperation

-0.44

EndContext

-0.43

WebControls

-0.43

POSITIVE LOGITS

AISSEE

0.53

↹

0.47

 Terkait

0.42

isbol

0.41

alnız

0.41

 Komunikasi

0.40

resz

0.40

 Prata

0.39

ậu

0.39

ity

0.39

Activations Density 0.009%

numeric representations, particularly those related to array sizes and indexing

code tags and punctuation

No Comments

No Known Activations