INDEX

Explanations

references to the concept of "home."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Réponses

-0.90

 SqlCommand

-0.86

 wikipagina

-0.84

исленность

-0.82

rophoresis

-0.80

CodeAttribute

-0.80

quehanna

-0.79

CodeAnalysis

-0.78

IsMutable

-0.77

redient

-0.77

POSITIVE LOGITS

 home

2.12

 Home

2.04

 HOME

2.00

HOME

1.97

home

1.97

Home

1.94

 homes

1.79

homes

1.72

 Homes

1.56

 HomeController

1.52

Activations Density 0.038%

references to the concept of "home."

No Comments

No Known Activations