INDEX

Explanations

references to evidence and evidence-based practices

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

Sentences starting with the word "evidence"

np_acts-logits-general · gemini-2.0-flash

evidence for or against

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

BarStyle

-0.66

Με

-0.65

 Normdatei

-0.59

UniformLocation

-0.59

enumii

-0.59

 useRouter

-0.59

ocities

-0.58

lidays

-0.57

 trouverez

-0.56

Geografia

-0.56

POSITIVE LOGITS

 supporting

0.62

 suggesting

0.60

 Evidence

0.59

 Evid

0.59

evidence

0.59

 against

0.56

Personensuche

0.56

Evidence

0.56

 EVIDENCE

0.56

 circunstan

0.54

Activations Density 0.245%

references to evidence and evidence-based practices

Sentences starting with the word "evidence"

evidence for or against

No Comments

No Known Activations