INDEX

Explanations

constructs related to class definitions and null checks 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

+#+

-0.75

enumi

-0.71

LookAnd

-0.70

TextWatcher

-0.65

 Theſe

-0.62

 themſelves

-0.61

 myſelf

-0.59

WriteTagHelper

-0.59

fillType

-0.57

<bos>

-0.56

POSITIVE LOGITS

MLLoader

0.64

 astore

0.55

?>>

0.52

Anmerkungen

0.52

 Dreyfus

0.51

StoryboardSegue

0.51

 FetchType

0.49

PrototypeOf

0.49

umbersome

0.49

Abbreviations

0.49

Activations Density 0.403%

constructs related to class definitions and null checks in programming code

No Comments

No Known Activations