INDEX

Explanations

patterns or structures in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

rd

-1.11

featureID

-0.87

 Thurman

-0.84

GeneratedValue

-0.82

 GlobalKey

-0.78

-0.77

 GenerationType

-0.76

SequentialGroup

-0.74

stateProvider

-0.74

 maxY

-0.74

POSITIVE LOGITS

1.48

1.31

1.29

1.26

1.22

1.20

1.11

1.08

1.04

1.02

Activations Density 0.586%

patterns or structures in data

No Comments

No Known Activations