INDEX

Explanations

quantitative references to "many" or "most" that indicate frequency or prevalence

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

 noget

-0.54

 gyhoeddwyd

-0.52

 legais

-0.52

 officielles

-0.51

ıştır

-0.51

]=>

-0.51

 ucapnya

-0.51

MigrationBuilder

-0.51

 suivants

-0.50

 Audiodateien

-0.49

POSITIVE LOGITS

 modern

0.69

Portale

0.67

 people

0.66

archiviato

0.64

contentLoaded

0.64

 employers

0.61

 dintre

0.59

ICATED

0.58

AddRange

0.58

 governments

0.58

Activations Density 0.340%

quantitative references to "many" or "most" that indicate frequency or prevalence

No Comments

No Known Activations