INDEX

Explanations

references to geographic locations and proper nouns in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Sinai

-0.67

IGraphics

-0.67

 hemispheres

-0.64

Mia

-0.61

gom

-0.61

 Pearce

-0.61

muk

-0.61

 mask

-0.60

mitian

-0.60

 Perrin

-0.59

POSITIVE LOGITS

Datuak

1.08

tonode

0.93

 disambiguazione

0.80

writeFieldEnd

0.75

 Spinal

0.75

 "..\..\

0.75

Personensuche

0.74

 Loot

0.74

Metallica

0.74

AsyncResult

0.72

Activations Density 0.813%

references to geographic locations and proper nouns in various contexts

No Comments

No Known Activations