INDEX

Explanations

occurrences of file and data handling operations in programming or documentation context

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

المناصب

-1.07

 autorytatywna

-0.91

TemporalType

-0.89

featureID

-0.89

Autoritní

-0.86

+#+

-0.83

bootstrapcdn

-0.82

gonic

-0.82

Tikang

-0.81

SequentialGroup

-0.79

POSITIVE LOGITS

IOException

0.58

olphins

0.49

reactivex

0.47

JsonIgnore

0.47

 redenen

0.46

 Janeiro

0.46

drums

0.46

Objekt

0.45

 Team

0.45

jer

0.44

Activations Density 0.027%

occurrences of file and data handling operations in programming or documentation context

No Comments

No Known Activations