INDEX

Explanations

terms related to accessibility and spatial arrangements in scientific contexts

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

access and inaccessibility

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.75

 CreateTagHelper

-0.71

enterOuterAlt

-0.68

 propOrder

-0.63

addCriterion

-0.61

 casais

-0.61

Vidite

-0.60

المناصب

-0.58

 ProtoMessage

-0.57

webElementXpaths

-0.57

POSITIVE LOGITS

 accessibility

0.61

 accessible

0.52

accessible

0.52

 access

0.52

 accesible

0.50

access

0.46

 ACCESS

0.45

Accessible

0.45

 acces

0.45

 Accessibility

0.44

Activations Density 0.297%

terms related to accessibility and spatial arrangements in scientific contexts

access and inaccessibility

No Comments

No Known Activations