INDEX

Explanations

terms related to mathematical optimization and decision-making processes

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

saraba

-0.62

Carriera

-0.52

webElement

-0.50

 coach

-0.47

 CreateTagHelper

-0.47

ppery

-0.46

CodeAttribute

-0.46

Abit

-0.44

IOL

-0.44

jur

-0.44

POSITIVE LOGITS

 minimum

1.82

 minim

1.71

 maximize

1.66

 minimization

1.66

 maximizing

1.65

 Minimum

1.65

minimum

1.62

 minimizing

1.62

 maximum

1.61

Minimum

1.60

Activations Density 1.077%

terms related to mathematical optimization and decision-making processes

No Comments

No Known Activations