INDEX

Explanations

code constructs related to functions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 للمعارف

-0.54

tabular

-0.51

 Wiktionnaire

-0.51

》.

-0.49

ston

-0.49

✭✭

-0.48

STON

-0.48

 Chwiliwch

-0.46

{(-

-0.46

 يتيمه

-0.45

POSITIVE LOGITS

Diweddarwch

0.79

 snippetHide

0.73

AccessorTable

0.71

 resourceCulture

0.67

 <>",

0.64

IUrlHelper

0.63

Portály

0.61

 ComVisible

0.61

 EClass

0.58

 Insee

0.57

Activations Density 0.150%

code constructs related to functions and methods

No Comments

No Known Activations