INDEX

Explanations

references to custom objects or products

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

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

ArrowToggle

-0.96

 חיצוניים

-0.91

utilisons

-0.86

tvguidetime

-0.83

ViewFeatures

-0.83

InitVars

-0.77

ChildIndex

-0.76

сылкі

-0.74

IntoConstraints

-0.73

 pinulongan

-0.72

POSITIVE LOGITS

isable

0.97

arily

0.91

izability

0.88

 tailored

0.87

 made

0.84

isation

0.83

izable

0.80

 tailor

0.79

ised

0.74

 Custom

0.71

Activations Density 0.045%

references to custom objects or products

No Comments

No Known Activations