INDEX

Explanations

references to "house" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ſmall

-0.81

 placent

-0.81

 ſeveral

-0.78

APL

-0.78

 allergies

-0.78

ergies

-0.76

 neceffary

-0.75

kegaard

-0.75

uſ

-0.73

 Canary

-0.73

POSITIVE LOGITS

 house

1.17

 House

1.12

 houses

1.08

House

1.03

 HOUSE

0.96

house

0.95

Houses

0.94

HOUSE

0.92

 Houses

0.90

houses

0.88

Activations Density 0.092%

references to "house" and related terms

No Comments

No Known Activations