INDEX

Explanations

references to identity and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.66

WebVitals

-0.66

MessageTagHelper

-0.66

存于互联网档案馆

-0.64

 pleaſure

-0.62

 Mecca

-0.62

IntoConstraints

-0.61

 NSCoder

-0.60

 heretics

-0.59

SourceChecksum

-0.59

POSITIVE LOGITS

 persona

0.75

persona

0.62

 role

0.59

 character

0.58

 roles

0.56

vatar

0.55

 personas

0.54

disfraz

0.53



0.53

 imperson

0.53

Activations Density 0.241%

references to identity and transformation

No Comments

No Known Activations