INDEX

Explanations

references to personal identity or self-identification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 initWithFrame

-0.65

IBOutlet

-0.62

paru

-0.56

Ál

-0.54

עת

-0.54

libft

-0.54

 cải

-0.51

tect

-0.50

/$',

-0.50

vist

-0.49

POSITIVE LOGITS

 lenker

0.82



0.80

 فريبيس

0.78

 onAnimation

0.74

 betweenstory

0.70

tanleria

0.70

 nahilalakip

0.67

msgTypes

0.66

Hochspringen

0.66

complexContent

0.66

Activations Density 0.163%

references to personal identity or self-identification

No Comments

No Known Activations