INDEX

Explanations

iterations of the word "back" 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

ształ

-0.71

 Winaray

-0.67

SharedDtor

-0.66

 defaultstate

-0.66

aarrggbb

-0.65

Diwedd

-0.65

ymal

-0.64

estacks

-0.63

DEA

-0.63

WillAppear

-0.62

POSITIVE LOGITS

stab

0.64

track

0.62

gam

0.59

tracking

0.59

seat

0.59

door

0.57

drops

0.57

wards

0.55

ManyToOne

0.51

firing

0.51

Activations Density 0.102%

iterations of the word "back" in various contexts

No Comments

No Known Activations