INDEX

Explanations

references to reports or studies

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

reports and released documents

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

 متعلقه

-0.66

 beginnetje

-0.65

verifyException

-0.57

transQ

-0.54

мужские

-0.52

PullParser

-0.51

HomeAsUpEnabled

-0.51

CrossRef

-0.50

RegressionTest

-0.50

Cyfarwyddwr

-0.50

POSITIVE LOGITS

 report

1.27

 Report

0.99

report

0.95

 study

0.94

Report

0.88

报告

0.84

 released

0.83

 research

0.82

 findings

0.81

 publication

0.80

Activations Density 0.035%

references to reports or studies

reports and released documents

No Comments

No Known Activations

references to reports or studies

reports and released documents

No Comments

No Known Activations