INDEX

Explanations

terms related to graphs and graph theory

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

FailureListener

-0.64

AddTagHelper

-0.61

getColumnIndex

-0.57

atguigu

-0.56

SuccessListener

-0.56

تمع

-0.53

haustible

-0.52

getStringExtra

-0.51

tainty

-0.51

醐

-0.51

POSITIVE LOGITS

 ExecuteAsync

0.71

StoreMessageInfo

0.69

 representation

0.64

 elettrico

0.63

 graphs

0.60

չ

0.59

 depicting

0.58

omotor

0.57

 مرئيه

0.56

 graphi

0.55

Activations Density 0.200%

terms related to graphs and graph theory

No Comments

No Known Activations