INDEX

Explanations

names of educational institutions and universities

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

State University names

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

 AssemblyCulture

-0.61

期刊论文

-0.49

 termica

-0.47

getchar

-0.47

WriteAttribute

-0.45

ecap

-0.45

itattu

-0.45

 noqa

-0.44

 ddelweddau

-0.44

EDEFAULT

-0.44

POSITIVE LOGITS

 University

0.59

 university

0.55

 president

0.51

ClientSize

0.49

 affiliate

0.49

university

0.48

University

0.47

 college

0.47

 College

0.47

 President

0.46

Activations Density 0.026%

names of educational institutions and universities

State University names

No Comments

No Known Activations