INDEX

Explanations

statistical references to values and parameters

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

pre

-0.58

-0.50

 pull

-0.46

userdetails

-0.45

Mo

-0.45

 system

-0.45

maq

-0.45

qu

-0.45

-0.44

POSITIVE LOGITS

LookAnd

1.02

:✨

0.89

 Paglinawan

0.86

IndentedString

0.86

 AssemblyCompany

0.84

 intptr

0.84

UnusedPrivate

0.82

DockStyle

0.82

onActivityResult

0.82

fjspx

0.82

Activations Density 1.073%

statistical references to values and parameters

No Comments

No Known Activations