INDEX

Explanations

phrases or terms related to technical discussions about programming and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

LabelTagHelper

-0.94

rawDesc

-0.89

MessageOf

-0.86

--]

-0.86

GEBURTSDATUM

-0.84

 GenerationType

-0.83

principalTable

-0.83

 EconPapers

-0.81

 defaultstate

-0.81

 насељу

-0.81

POSITIVE LOGITS

 incidentally

0.48

 gelegen

0.44

 admittedly

0.43

 thankfully

0.42

0.41

 egyéb

0.40

<u>

0.39

 blanches

0.38

 kemeja

0.38

 appréci

0.38

Activations Density 0.868%

phrases or terms related to technical discussions about programming and algorithms

No Comments

No Known Activations