INDEX

Explanations

parameters and return values in function documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

enumi

-0.72

AccessorTable

-0.59

Попис

-0.52

Sucesor

-0.49

GRANTED

-0.47

enumii

-0.46

setVerticalGroup

-0.45

ChildScrollView

-0.45

้อย

-0.45

 neutrals

-0.45

POSITIVE LOGITS

 autorytatywna

0.81

holdet

0.77

 hvilken

0.77

opcional

0.75

 Either

0.73

indicates

0.71

Specifies

0.71

Indicates

0.69

 specifies

0.69

 quelcon

0.68

Activations Density 0.333%

parameters and return values in function documentation

No Comments

No Known Activations