INDEX

Explanations

code snippets and programming-related terms

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

DockStyle

-0.81

ItemBackground

-0.76

RenderAtEndOf

-0.68

:✨

-0.62

styleable

-0.62

stdc

-0.60

SharedCtor

-0.59

Mis

-0.57

ccoli

-0.57

 axis

-0.57

POSITIVE LOGITS

 fall

0.55

fall

0.54

Fall

0.54

 FALL

0.52

чук

0.51

 care

0.50

 Fall

0.50

 males

0.49

 male

0.49

 perturb

0.49

Activations Density 0.053%

code snippets and programming-related terms

No Comments

No Known Activations