INDEX

Explanations

occurrences of the word "len" and its variations, indicating a focus on length-related terms

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

starting with "Len" or "len"

np_acts-logits-general · gemini-2.0-flash

lenity, Lenhart, Leonard, lensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Demografia

-0.58

 Butterfield

-0.54

tute

-0.54

 advance

-0.53

MILL

-0.52

Hoc

-0.51

Mill

-0.50

越高

-0.50

Erb

-0.50

 carbox

-0.50

POSITIVE LOGITS

 oprot

0.81

 lenker

0.78

LEN

0.78

 MainAxisSize

0.76

 Lenny

0.71

 SqlCommand

0.69

PerformLayout

0.69

曖昧さ回避

0.67

كويكب

0.66

 Blen

0.66

Activations Density 0.031%

occurrences of the word "len" and its variations, indicating a focus on length-related terms

starting with "Len" or "len"

lenity, Lenhart, Leonard, lensing

No Comments

No Known Activations

occurrences of the word "len" and its variations, indicating a focus on length-related terms

starting with "Len" or "len"

lenity, Lenhart, Leonard, lensing

No Comments

No Known Activations