INDEX

Explanations

references to roads and road-related concepts 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

Życiorys

-1.04

arXiv

-0.96

 HasFactory

-0.89

Aktualisiert

-0.89

 femeninos

-0.88

 FishBase

-0.83

 Kaufman

-0.82

InjectAttribute

-0.82

 denominations

-0.82

 himſelf

-0.81

POSITIVE LOGITS

 Road

1.51

 road

1.49

 roads

1.48

road

1.34

 ROAD

1.32

 Roads

1.32

Road

1.28

roads

1.19

Roads

1.17

ROAD

1.09

Activations Density 0.036%

references to roads and road-related concepts in various contexts

No Comments

No Known Activations