INDEX

Explanations

references to knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

StructEnd

-0.61

verts

-0.56

 المعيارى

-0.54

SBATCH

-0.53

Mui

-0.52

 comisión

-0.52

 rehabilitate

-0.52

 rebels

-0.52

vál

-0.51

cartier

-0.51

POSITIVE LOGITS

 knowledge

1.01

knowledge

0.96

 Knowledge

0.94

Knowledge

0.93

 knowled

0.79

 KNOWLEDGE

0.77

 base

0.70

 propOrder

0.70

gain

0.67

ANDUM

0.66

Activations Density 0.176%

references to knowledge and understanding

No Comments

No Known Activations