INDEX

Explanations

references to custom elements or features in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ArrowToggle

-0.84

 pinulongan

-0.79

 AssemblyVersion

-0.76

Parcelize

-0.75

 חיצוניים

-0.74

tvguidetime

-0.71

WebVitals

-0.71

 financeira

-0.70

сылкі

-0.70

utilisons

-0.69

POSITIVE LOGITS

 Custom

0.99

 custom

0.99

 tailored

0.96

 tailor

0.89

isable

0.88

Custom

0.87

custom

0.87

 CUSTOM

0.87

setCustom

0.87

CUSTOM

0.84

Activations Density 0.068%

references to custom elements or features in various contexts

No Comments

No Known Activations