INDEX

Explanations

references to built-in features or components in various contexts

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

 виправивши

-0.61

 useContext

-0.58

 AssemblyCompany

-0.58

CreateInfo

-0.56

ResumeLayout

-0.55

 يتيمه

-0.54

createCanvas

-0.52

 незавершена

-0.51

hips

-0.51

sianic

-0.50

POSITIVE LOGITS

mybatisplus

0.77

IndentedString

0.58

rxjs

0.55

RTLD

0.52

setOpen

0.51

Bros

0.48

iteration

0.47

 Bros

0.47

DataPropertyName

0.46

ógy

0.46

Activations Density 0.232%

references to built-in features or components in various contexts

No Comments

No Known Activations