INDEX

Explanations

sections of text that are mostly devoid of content or are placeholders

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

Follows certain punctuation or formatting

np_acts-logits-general · gemini-2.0-flash

producing theperiod startpatients with

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 OFDb

-0.59

 Shakspeare

-0.57

 lande

-0.55

agerie

-0.54

 mariner

-0.54

yet

-0.53

 maiden

-0.53

 notion

-0.53

లాలు

-0.52

 concept

-0.52

POSITIVE LOGITS

 himself

0.64

rmtree

0.64

him

0.63

himself

0.61

bootstrapcdn

0.60

 others

0.57

躇

0.55

DockStyle

0.55

Relevant

0.53

his

0.53

Activations Density 0.047%

sections of text that are mostly devoid of content or are placeholders

Follows certain punctuation or formatting

producing theperiod startpatients with

No Comments

No Known Activations