INDEX

Explanations

dimensions and specifications related to images or prints

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

shadowOpacity

-0.35

 successful

-0.33

 success

-0.33

load

-0.29

successful

-0.28

Appearances

-0.28

 phép

-0.28

 involve

-0.28

isSuccessful

-0.28

 loob

-0.28

POSITIVE LOGITS

 صوتيه

0.95

Personendaten

0.81

 Biôgrafia

0.76

StoryboardSegue

0.75

sizeCache

0.75

 CreateTagHelper

0.66

EndProject

0.66

 NSCoder

0.65

 resourceCulture

0.63

CodedInputStream

0.63

Activations Density 0.004%

dimensions and specifications related to images or prints

No Comments

No Known Activations