INDEX

Explanations

references to specific platforms or systems

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

"platform" and related terms

np_acts-logits-general · gemini-2.0-flash

platform

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OrNil

-0.76

EDEFAULT

-0.74

 AssemblyCulture

-0.68

ⓧ

-0.66

InstanceState

-0.64

RTLE

-0.64

]")]

-0.63

 endforeach

-0.61

 cotone

-0.60

seamnă

-0.60

POSITIVE LOGITS

 platforms

1.08

 platt

0.99

 Platforms

0.95

 Platt

0.92

platforms

0.89

Platt

0.85

 Plattform

0.79

 平台

0.76

Platforms

0.76

latform

0.69

Activations Density 0.110%

references to specific platforms or systems

"platform" and related terms

platform

No Comments

No Known Activations