INDEX

Explanations

programming syntax related to assignments and variable definitions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ítulo

-0.56

GEBURTSDATUM

-0.52

nemia

-0.50

lwjgl

-0.49

 surla

-0.48

 Issus

-0.47

ướp

-0.45

ביוגרפיה

-0.45

liquer

-0.45

ributions

-0.45

POSITIVE LOGITS

rungsseite

0.77

contentLoaded

0.75

protoimpl

0.73

uxxxx

0.71

 utafitiHapana

0.69

 iprot

0.64

onViewCreated

0.61

rån

0.61

basicConfig

0.60

varargin

0.59

Activations Density 0.294%

programming syntax related to assignments and variable definitions

No Comments

No Known Activations