INDEX

Explanations

references to method definitions and instance variables in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ByUserId

-0.49

尤

-0.45

ждую

-0.45

 kalangan

-0.44

പ

-0.44

örper

-0.43

dfrac

-0.42

CEPT

-0.40

ecken

-0.40

Nth

-0.40

POSITIVE LOGITS

 propOrder

1.19

 unknownFields

0.91

AndEndTag

0.82

InitVars

0.81

>{@

0.79

UnusedPrivate

0.78

GEBURTSDATUM

0.78

synthesize

0.77

 mergeFrom

0.76

parsedMessage

0.76

Activations Density 0.052%

references to method definitions and instance variables in programming code

No Comments

No Known Activations