INDEX

Explanations

terms related to bipartite structures and bi-layered concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 <<<<<<<<<<<<<<

-0.84

 transfieras

-0.81

UserScript

-0.76

ImageContext

-0.75

MessageOf

-0.75

InputBorder

-0.74

Efq

-0.71

ContentLoaded

-0.70

Sucesor

-0.70

StructEnd

-0.67

POSITIVE LOGITS

bi

0.87

Bi

0.75

Bid

0.72

Bid

0.69

BID

0.67

 Би

0.65

BID

0.64

bid

0.63

Bir

0.63

bid

0.61

Activations Density 0.274%

terms related to bipartite structures and bi-layered concepts

No Comments

No Known Activations