INDEX

Explanations

connections and relationships among various subjects or ideas

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

ValueStyle

-1.06

 initComponents

-0.95

NameInMap

-0.90

таратура

-0.85

 Roskov

-0.84

 AssemblyProduct

-0.81

DockStyle

-0.79

UnusedPrivate

-0.77

 שוליים

-0.77

ImageContext

-0.77

POSITIVE LOGITS

 situation

0.85

 entire

0.79

 timeline

0.75

 approach

0.74

 timeframe

0.73

 environment

0.73

 palette

0.73

 portion

0.72

 framework

0.72

 lineup

0.72

Activations Density 0.445%

connections and relationships among various subjects or ideas

No Comments

No Known Activations