INDEX

Explanations

terms related to variables and dynamic properties in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

pielen

-0.64

pielt

-0.62

pannt

-0.61

 Cullen

-0.59

timmt

-0.52

 Griswold

-0.52

ArgsConstructor

-0.50

HAV

-0.49

Sae

-0.49

AddTagHelper

-0.48

POSITIVE LOGITS

CH

1.46

CH

1.42

ch

1.40

ch

1.38

Ch

1.34

Ch

1.32

ACH

1.25

chi

1.22

Chi

1.19

chi

1.19

Activations Density 4.440%

terms related to variables and dynamic properties in scientific or technical contexts

No Comments

No Known Activations