INDEX

Explanations

technical terms related to software or code management

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

 itſelf

-1.06

 Monfieur

-1.06

 Theſe

-0.97

 myſelf

-0.94

 feroit

-0.87

 himſelf

-0.86

ſelf

-0.85

 whoſe

-0.84

 themſelves

-0.83

 poffe

-0.82

POSITIVE LOGITS

<unused63>

0.73

<unused62>

0.73

UserScript

0.72

<unused61>

0.71

<unused60>

0.66

帖最后由

0.62

 <<<<<<<<<<<<<<

0.60

 snippetHide

0.57

fjspx

0.53

 cref

0.52

Activations Density 2.374%

technical terms related to software or code management

No Comments

No Known Activations