INDEX

Explanations

statistical values or data in the context of analysis

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

 angelo

-0.67

Kuch

-0.64

مصادر

-0.63

 Billings

-0.62

плек

-0.62

gue

-0.61

 Kuch

-0.61

 ervoor

-0.61

rout

-0.60

 dure

-0.60

POSITIVE LOGITS

subsection

1.16

subsubsection

1.11

ViewFeatures

0.80

Demografie

0.76

unhofer

0.73

اریخ

0.72

FTE

0.71

PyExc

0.71

öscht

0.71

*/].

0.70

Activations Density 0.687%

statistical values or data in the context of analysis

No Comments

No Known Activations