INDEX

Explanations

structured data output and discussions of statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Identyfik

-0.66

 réguli

-0.61

 humaines

-0.58

 виправивши

-0.58

SequentialGroup

-0.58

ouncements

-0.57

IntoConstraints

-0.56

Xna

-0.55

 szóci

-0.55

 numberWith

-0.55

POSITIVE LOGITS

 historians

0.89

 reconstructions

0.75

 rekon

0.74

 reconstructed

0.74

 historian

0.74

 reconstru

0.71

 historical

0.71

Historic

0.69

 reconstruct

0.69

 reconstruction

0.68

Activations Density 0.625%

structured data output and discussions of statistics

No Comments

No Known Activations