INDEX

Explanations

references to programming languages and code-related terminology

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

Text or code snippets including "X"

np_acts-logits-general · gemini-2.0-flash

words starting with X

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

lay

-0.48

 molding

-0.44

 Ressources

-0.43

Evaporation

-0.42

ער

-0.41

put

-0.41

routeProvider

-0.40

 Greenfield

-0.40

 Alma

-0.40

POSITIVE LOGITS

Xer

1.07

 Xanth

1.04

Xs

1.00

Xy

0.99

xer

0.94

Xo

0.93

Xa

0.92

 xanth

0.91

Xt

0.90

xt

0.89

Activations Density 0.512%

references to programming languages and code-related terminology

Text or code snippets including "X"

words starting with X

No Comments

No Known Activations