INDEX

Explanations

references to programming constructs or code-related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+:+

-0.60

IndentedString

-0.58

awin

-0.50

richTextPanel

-0.50

onuc

-0.49

:+:

-0.48

 aksi

-0.48

DockStyle

-0.47

oulders

-0.47

Worth

-0.47

POSITIVE LOGITS

 type

0.74

 gener

0.71

 typedef

0.62

 types

0.62

 subtype

0.59

ty

0.58

 Type

0.58

 generic

0.58

typeparam

0.58

 tipos

0.57

Activations Density 0.811%

references to programming constructs or code-related issues

No Comments

No Known Activations