INDEX

Explanations

terms related to restrictions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 HasFactory

-0.67

Juf

-0.67

 censiti

-0.67

zczegól

-0.67

Personendaten

-0.65

PHONY

-0.62

 Emergence

-0.61

 vrai

-0.61

absence

-0.61

 Arag

-0.61

POSITIVE LOGITS

 restrict

1.68

limit

1.61

 limit

1.61

 restriction

1.54

 Limit

1.54

 restricting

1.53

 limiting

1.50

 limitation

1.45

Limit

1.43

 restricts

1.39

Activations Density 0.093%

terms related to restrictions or limitations

No Comments

No Known Activations