INDEX

Explanations

phrases and words that indicate processes and systems in an educational or administrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.80

 AssemblyCulture

-0.75

expandindo

-0.71

ScopeManager

-0.71

oneofs

-0.70

 فريبيس

-0.69

OGND

-0.66

HostException

-0.62

MENAFN

-0.62

Espèce

-0.62

POSITIVE LOGITS

 imaging

0.69

 investigative

0.68

 publishing

0.64

 manufacturing

0.59

 voting

0.59

publishing

0.58

sampling

0.58

inigungs

0.57

 trading

0.57

wapV

0.56

Activations Density 1.254%

phrases and words that indicate processes and systems in an educational or administrative context

No Comments

No Known Activations