INDEX

Explanations

statements about necessity, likelihood, and recommendations

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

"is" followed by an adjective

np_acts-logits-general · gemini-2.0-flash

necessity and possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.68

 ujednoznacz

-0.60

OGND

-0.59

 uLocal

-0.55

 iprot

-0.54

发表于

-0.54

delwed

-0.52

ValueStyle

-0.52

 ModelExpression

-0.49

енча

-0.48

POSITIVE LOGITS

 impossible

0.43

oneer

0.40

 оши

0.37

 imperative

0.36

 ومن

0.35

ivasan

0.35

 possible

0.34

common

0.34

 advisable

0.34

deauna

0.33

Activations Density 0.359%

statements about necessity, likelihood, and recommendations

"is" followed by an adjective

necessity and possibility

No Comments

No Known Activations