INDEX

Explanations

terms related to scientific experiments and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 duele

-0.80

 kasarigan

-0.77

rrggbb

-0.71

 étoit

-0.70

 étoient

-0.70

 muere

-0.69

 immobilier

-0.68

 anún

-0.67

 girdle

-0.67

ContextHolder

-0.67

POSITIVE LOGITS

 Experiment

1.00

 experiment

0.96

 experiments

0.96

 Experiments

0.95

Experiment

0.93

 experimental

0.90

 Experimental

0.83

 EXPERIMENT

0.81

 experimentally

0.81

Experiments

0.80

Activations Density 0.145%

terms related to scientific experiments and methodologies

No Comments

No Known Activations