INDEX

Explanations

different styling specifications in text or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SourceChecksum

-0.90

 auffi

-0.76

 myſelf

-0.69

 itſelf

-0.67

Eſ

-0.65

Egypte

-0.64

Smarty

-0.63

 flint

-0.63

eriksaan

-0.61

 Smarty

-0.61

POSITIVE LOGITS

style

1.77

STYLE

0.92

 style

0.82

Collegamenti

0.70

Style

0.65

styled

0.63

styles

0.59

 STYLE

0.56

 estilo

0.54

 Style

0.52

Activations Density 0.020%

different styling specifications in text or code

No Comments

No Known Activations