INDEX

Explanations

references to layers in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 pinulongan

-0.88

 resourceCulture

-0.76

TagMode

-0.74

DotNetBar

-0.73

">—

-0.72

 الحره

-0.71

MessageTagHelper

-0.70

PreferredItem

-0.69

uxxxx

-0.69

thâu

-0.68

POSITIVE LOGITS

 Layers

1.18

 layers

1.13

 LAYER

1.11

 Layer

1.09

Layers

1.02

 layer

0.99

layers

0.97

layer

0.95

LAY

0.90

Layer

0.89

Activations Density 0.169%

references to layers in a scientific or technical context

No Comments

No Known Activations