INDEX

Explanations

references to features in various contexts

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

"feature" and related terms

np_acts-logits-general · gemini-2.0-flash

feature selection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Искәрмәләр

-0.68

thâu

-0.67

 Abbé

-0.66

PVA

-0.65

ագրություններ

-0.64

IndentedString

-0.64

 dõi

-0.63

 Abbe

-0.60

ILON

-0.60

opsida

-0.58

POSITIVE LOGITS

 prominently

0.97

 features

0.96

 feature

0.88

features

0.88

 Features

0.84

 Feature

0.81

 FEATURE

0.80

Features

0.80

 FEATURES

0.74

feature

0.73

Activations Density 0.174%

references to features in various contexts

"feature" and related terms

feature selection

No Comments

No Known Activations