INDEX

Explanations

references to rank or hierarchical positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ITTEN

-0.76

 aceptas

-0.75

Gön

-0.65

PLW

-0.64

 kohdetta

-0.62

verwijspagina

-0.61

 Avila

-0.61

EObject

-0.61

wirtschaft

-0.60

VIOUS

-0.60

POSITIVE LOGITS

 rank

3.21

 RANK

2.96

 Rank

2.96

 ranks

2.91

rank

2.90

Rank

2.85

 Ranks

2.76

 ranking

2.64

RANK

2.63

ranks

2.53

Activations Density 0.073%

references to rank or hierarchical positions

No Comments

No Known Activations