INDEX

Explanations

references to individuals and their relationships to specific locations or roles

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

[location] is for.

np_acts-logits-general · gemini-2.0-flash

locations and activities

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

LookAnd

-0.72

//

-0.71

 OFDb

-0.68

StructEnd

-0.64

BagLayout

-0.61

 بيها

-0.59

Geplaatst

-0.58

InvalidProtocol

-0.56

 föruts

-0.51

 <=",

-0.51

POSITIVE LOGITS

 doing

1.08

 enjoying

1.02

 ready

0.96

 trying

0.95

 working

0.93

 performing

0.93

doing

0.92

 waiting

0.91

 listening

0.90

 fighting

0.90

Activations Density 0.237%

references to individuals and their relationships to specific locations or roles

[location] is for.

locations and activities

No Comments

No Known Activations