INDEX

Explanations

terminology related to testing and assessment in various contexts

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

targets and subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 برانيه

-0.41

verwijspagina

-0.39

createStatement

-0.38

 noix

-0.38

 informée

-0.36

 screw

-0.35

 vibes

-0.35

гин

-0.35

ortions

-0.34

isional

-0.34

POSITIVE LOGITS

 Targets

0.73

 targets

0.69

target

0.63

targets

0.61

対象

0.60

subjects

0.60

 Target

0.59

Subjects

0.59

 target

0.59

subject

0.59

Activations Density 0.078%

terminology related to testing and assessment in various contexts

targets and subjects

No Comments

No Known Activations