INDEX

Explanations

code annotations and auto-generated comments or directives

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

 Monfieur

-0.82

InputTagHelper

-0.77

quelize

-0.75

msgSender

-0.70

tonode

-0.69

 EClass

-0.68

 myſelf

-0.68

Efq

-0.61

FormTagHelper

-0.59

bitField

-0.59

POSITIVE LOGITS

 مشين

0.62



0.62

 Auto

0.57

 auto

0.56

generated

0.56

 generated

0.53

 code

0.52

ंदीखरीदारी

0.51

abestanden

0.49

PRNewswire

0.49

Activations Density 0.074%

code annotations and auto-generated comments or directives

No Comments

No Known Activations