INDEX

Explanations

the beginning of new sections or paragraphs in text

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

section titles or headings

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

stdc

-0.79

 SqlDbType

-0.73

 Bioaccumulative

-0.69

رشف

-0.67

 esternos

-0.67

sieur

-0.64

ReusableCell

-0.64

ImageContext

-0.61

SBATCH

-0.60

openqa

-0.59

POSITIVE LOGITS

↵↵

0.77

0.76

__))

0.74

<eos>

0.73

↵↵↵

0.69

("]");

0.66

?>>

0.66

↵↵↵↵

0.65

 kasarigan

0.64

↵

0.62

Activations Density 0.389%

the beginning of new sections or paragraphs in text

section titles or headings

No Comments

No Known Activations