INDEX

Explanations

programming-related terms and concepts

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

assignments and comparisons

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

TagMode

-0.42

InOut

-0.38

++.

-0.36

يميديا

-0.36

NSYLVANIA

-0.36

plish

-0.35

AddHtmlAttribute

-0.35

Be

-0.35

++]=

-0.35

Blu

-0.34

POSITIVE LOGITS

Personendaten

0.65

addPreferredGap

0.58

 članak

0.54

addContainerGap

0.52

이나

0.52

Datuak

0.51

 CreateTagHelper

0.51

LabelTagHelper

0.48

 tartalomajánló

0.47

 Audiodateien

0.47

Activations Density 0.046%

programming-related terms and concepts

assignments and comparisons

No Comments

No Known Activations