INDEX

Explanations

entities, particularly names and references to people or authors in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

PerformLayout

-0.92

 itſelf

-0.87

 ModelExpression

-0.85

StoryboardSegue

-0.84

AutoScale

-0.84

例文帳に追加

-0.80

 himſelf

-0.80

 tartalomajánló

-0.77

}\]

-0.77

 themſelves

-0.74

POSITIVE LOGITS

Rptr

0.50

Viitteet

0.46

0.45

live

0.43

Referanser

0.40

("

0.39

 Normdatei

0.38

 yarar

0.38

ुत

0.38

 live

0.37

Activations Density 0.193%

entities, particularly names and references to people or authors in academic contexts

No Comments

No Known Activations