INDEX

Explanations

terms related to processes or functions in computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stered

-0.51

 Patri

-0.49

Retain

-0.49

ogr

-0.46

wz

-0.46

Saved

-0.46

 patri

-0.45

Skipped

-0.44

zku

-0.43

Returned

-0.43

POSITIVE LOGITS

parsedMessage

1.09

 initComponents

0.82

 BoxDecoration

0.78

+#+#

0.75

 للمعارف

0.74

WithIOException

0.73

setViewportView

0.72

 GenerationType

0.69

SequentialGroup

0.68

AddTagHelper

0.67

Activations Density 0.452%

terms related to processes or functions in computing

No Comments

No Known Activations