INDEX

Explanations

patterns related to numerical sequences and their interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

iocene

-0.79

akaian

-0.71

endphp

-0.68

Geneva

-0.61

AxisAlignment

-0.58

bpy

-0.58

//

-0.58

 détour

-0.56

 Geneva

-0.55

 strconv

-0.54

POSITIVE LOGITS

bootstrapcdn

0.84

ConstraintMaker

0.61

queryInterface

0.59

rungsseite

0.57

actionMode

0.57

StoryboardSegue

0.57

 kaynağından

0.56

stdlib

0.55

 désolés

0.54

Havolalar

0.53

Activations Density 0.284%

patterns related to numerical sequences and their interpretations

No Comments

No Known Activations