INDEX

Explanations

references to various types of pools and associated structures

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

 متعلقه

-0.84

psons

-0.82

 Johanna

-0.79

 condamné

-0.75

 Ignacio

-0.70

 Bellingham

-0.70

UHD

-0.70

 Johnstone

-0.68

Joh

-0.68

Linha

-0.66

POSITIVE LOGITS

 pool

1.82

 pools

1.79

 Pool

1.64

 POOL

1.57

 Pools

1.49

pools

1.48

Pools

1.48

pool

1.48

Pool

1.39

POOL

1.24

Activations Density 0.056%

references to various types of pools and associated structures

No Comments

No Known Activations