INDEX

Explanations

code-related terms and functions for file manipulation and data processing

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

StoryboardSegue

-0.92

+#+#

-0.74

 للمعارف

-0.74

AndEndTag

-0.69

 initComponents

-0.67

ConstraintMaker

-0.66

AddTagHelper

-0.66

PerformLayout

-0.65

rouvez

-0.64

agulation

-0.63

POSITIVE LOGITS

bufio

0.51

readlines

0.48

 environnement

0.47

AppendLine

0.46

<bos>

0.44

splitlines

0.44

lese

0.43

multiline

0.42

tsv

0.42

ocr

0.41

Activations Density 0.260%

code-related terms and functions for file manipulation and data processing

No Comments

No Known Activations