INDEX

Explanations

occurrences of the word "number"

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

Text preceding a number

np_acts-logits-general · gemini-2.0-flash

biographical executive list

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

 lenker

-0.68

الحياه

-0.66

 mergeFrom

-0.63

 AssemblyCulture

-0.56

protoimpl

-0.54

ValueStyle

-0.54

ReusableCell

-0.54

"}";

-0.53

 发表于

-0.53

WriteAttribute

-0.52

POSITIVE LOGITS

 itſelf

0.97

 Majefty

0.91

 themſelves

0.84

 theſe

0.82

 myſelf

0.79

 ſeveral

0.78

 pleaſure

0.78

 ſhall

0.76

 faſt

0.76

 greateſt

0.75

Activations Density 0.248%

occurrences of the word "number"

Text preceding a number

biographical executive list

No Comments

No Known Activations