INDEX

Explanations

documentation comments and function descriptors in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

principalTable

-0.89

MessageOf

-0.74

SourceChecksum

-0.68

 propOrder

-0.67

 виправивши

-0.67

 CanadaChoose

-0.66

setVerticalGroup

-0.64

Билгалдахарш

-0.64

IUrlHelper

-0.63

expandindo

-0.62

POSITIVE LOGITS

Ego

0.40

Ego

0.36

 system

0.36

 general

0.36

 примі

0.35

 compensation

0.35

 person

0.35

 manzanas

0.34

 method

0.34

 ability

0.33

Activations Density 0.005%

documentation comments and function descriptors in code

No Comments

No Known Activations