INDEX

Explanations

terms related to processes, conditions, and classifications in various contexts, particularly in technical or operational descriptions

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

preceding verbs and conjunctions

np_acts-logits-general · gemini-2.0-flash

requirements and capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

代わりに

-0.44

 riferimento

-0.44

 pleno

-0.43

opter

-0.43

 altså

-0.43

ValueStyle

-0.41

 chóng

-0.40

 doel

-0.40

 Walden

-0.40

最大的

-0.39

POSITIVE LOGITS

 nécess

0.76

QMetaType

0.75

 resourceCulture

0.75

 requiring

0.75

 OFDb

0.75

లాలు

0.74

 للاسماء

0.74

 виправивши

0.73

 Himo

0.72

ContentAsync

0.72

Activations Density 0.688%

terms related to processes, conditions, and classifications in various contexts, particularly in technical or operational descriptions

preceding verbs and conjunctions

requirements and capabilities

No Comments

No Known Activations