INDEX

Explanations

identifiers and values associated with specific measurements or algorithms in technical contexts

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

HTML or XML tags, attributes, or code

np_acts-logits-general · gemini-2.0-flash

analyzing, backups

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

 Theſe

-0.63

wiſe

-0.62

 Autorizaciones

-0.60

 Shakspeare

-0.59

 محفوظة

-0.58

AccessorTable

-0.56

 pleaſure

-0.56

 Majefty

-0.55

 itſelf

-0.55

 ―――――

-0.55

POSITIVE LOGITS

LookAnd

0.59

}{*}{

0.51

 isempty

0.50

RuleContext

0.50

setof

0.50

ierto

0.49

Sand

0.48

hof

0.47

 "'");

0.46

ineno

0.46

Activations Density 0.698%

identifiers and values associated with specific measurements or algorithms in technical contexts

HTML or XML tags, attributes, or code

analyzing, backups

No Comments

No Known Activations