INDEX

Explanations

terms related to connecting or establishing relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

gdx

-0.94

iermark

-0.88

 vaut

-0.86

 MediatR

-0.86

 UnityEditor

-0.81

Stderr

-0.80

writeField

-0.78

 defStyle

-0.76

PreferredItem

-0.76

 DevExpress

-0.74

POSITIVE LOGITS

 CONNECT

1.69

 connection

1.66

 connects

1.64

 connect

1.64

 connecting

1.58

 connected

1.58

 connections

1.57

 connectivity

1.55

 conne

1.53

CONNECT

1.52

Activations Density 0.101%

terms related to connecting or establishing relationships

No Comments

No Known Activations