INDEX

Explanations

names and references related to specific individuals and locations 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Snell

-0.77

ongiorno

-0.76

logenetic

-0.73

 Drog

-0.72

 Arad

-0.72

 Gerv

-0.72

 Mier

-0.69

----</

-0.69

ilene

-0.68

Ise

-0.67

POSITIVE LOGITS

 Dixie

0.90

Dixie

0.88

 McClure

0.85

);

0.81

ities

0.80

 Carr

0.79

ToHex

0.79

Dix

0.79

thâu

0.78

 Beatty

0.78

Activations Density 2.382%

names and references related to specific individuals and locations in various contexts

No Comments

No Known Activations