INDEX

Explanations

references to academic publications and citations

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

hup

-0.55

 metav

-0.44

cloudflare

-0.43

copie

-0.42

 Anexo

-0.40

woff

-0.40

 Cámara

-0.40

 /\.(

-0.40

 progre

-0.40

盤

-0.39

POSITIVE LOGITS

 Volume

0.88

volume

0.85

vol

0.85

 volume

0.82

Vol

0.81

Volume

0.80

Vol

0.80

vol

0.74

VOLUME

0.73

NOPQRST

0.73

Activations Density 0.377%

references to academic publications and citations

No Comments

No Known Activations