INDEX

Explanations

HTML span elements with specific attributes

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

HTML span tag

np_acts-logits-general · gemini-2.0-flash

html span tag

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

 Mühl

-0.78

tinggi

-0.73

sizeCache

-0.72

usercontent

-0.71

 Seventh

-0.70

EndProject

-0.70

Officers

-0.67

SIO

-0.67

 Herrick

-0.67

liothèque

-0.67

POSITIVE LOGITS

span

1.65

 SPAN

1.26

 span

1.26

spans

1.20

 Span

1.16

Span

1.15

SPAN

1.11

 spans

1.05

MessageTagHelper

0.90

 spanned

0.87

Activations Density 0.083%

HTML span elements with specific attributes

HTML span tag

html span tag

No Comments

No Known Activations