INDEX

Explanations

references to doors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

gaande

-0.69

eclampsia

-0.61

 sauvages

-0.56

 Campionato

-0.56

 poética

-0.55

reszcie

-0.54

 tevreden

-0.53

 furrowed

-0.53

 Lerner

-0.53

ollett

-0.52

POSITIVE LOGITS

 door

4.63

 Door

4.08

door

4.04

Door

3.94

 DOOR

3.94

 doors

3.85

 Doors

3.35

doors

3.24

DOOR

3.14

Doors

3.05

Activations Density 0.054%

references to doors

No Comments

No Known Activations