INDEX

Explanations

references to layers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.93

 resourceCulture

-0.87

 للمعارف

-0.79

MessageTagHelper

-0.78

migrationBuilder

-0.75

">—

-0.74

MemoryWarning

-0.73

PreferredItem

-0.72

WritableDatabase

-0.72

thâu

-0.72

POSITIVE LOGITS

 Layers

1.34

 layers

1.29

Layers

1.21

 LAYER

1.17

 Layer

1.16

layers

1.09

 layer

1.08

layer

1.04

Layer

1.01

LAYER

1.00

Activations Density 0.149%

references to layers in various contexts

No Comments

No Known Activations