INDEX

Explanations

initial markers or formatting indicators in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

luß

-0.80

"]];

-0.65

 läßt

-0.65

 Whilst

-0.64

 Schluß

-0.61

Whilst

-0.61

 didalam

-0.61

!!!

-0.60

 disini

-0.59

\#

-0.57

POSITIVE LOGITS

 Roskov

0.78

الحياه

0.77

 NDEBUG

0.75

Попис

0.72

intios

0.71

setVerticalGroup

0.66

ContentAlignment

0.66

Rhestr

0.65

zzleHttp

0.65

addCriterion

0.64

Activations Density 0.236%

initial markers or formatting indicators in documents

No Comments

No Known Activations