INDEX

Explanations

specific configurations and settings related to software environments

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

Code-related tokens followed by punctuation/symbols

np_acts-logits-general · gemini-2.0-flash

Absinthe subscriptions and receive calls

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-1.14

ſelves

-1.02

 Reſ

-0.99

 Diſ

-0.98

ſelf

-0.90

wiſe

-0.89

 Anſ

-0.86

 myſelf

-0.86

 ་་

-0.86

 EconPapers

-0.84

POSITIVE LOGITS

0.77

0.70

!(

0.68

0.64

0.59

0.58

((

0.57

LabelTagHelper

0.55

do

0.54

RenderAtEndOf

0.53

Activations Density 0.283%

specific configurations and settings related to software environments

Code-related tokens followed by punctuation/symbols

Absinthe subscriptions and receive calls

No Comments

No Known Activations