INDEX

Explanations

references to location and presence

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

tanleria

-0.71

AddTagHelper

-0.57

AndEndTag

-0.56

enterOuterAlt

-0.54

 CreateTagHelper

-0.53

SerializedSize

-0.52

ftagPool

-0.51

+:+

-0.51

msgTypes

-0.48

SourceChecksum

-0.47

POSITIVE LOGITS

 varandra

0.40

nezeu

0.39

paigns

0.36

 coroa

0.36

 elaborate

0.35

 elabor

0.35

 enriched

0.34

 mapping

0.34

 sürü

0.34

tershire

0.34

Activations Density 0.058%

references to location and presence

No Comments

No Known Activations