INDEX

Explanations

information related to testing and evaluations in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

RenderAtEndOf

-0.70

 CreateTagHelper

-0.65

ValueStyle

-0.62

出版年

-0.61

новниш

-0.60

 jspb

-0.56

jspb

-0.50

 Himo

-0.49

principalTable

-0.49

Démographie

-0.48

POSITIVE LOGITS

bkz

0.59

0.54

 nonatomic

0.54

՚

0.52

WriteLiteral

0.52

chaffenheit

0.52

Boas

0.52

󠁿

0.51

 Audiodateien

0.50

belongsTo

0.50

Activations Density 2.812%

information related to testing and evaluations in a technical context

No Comments

No Known Activations