INDEX

Explanations

mathematical symbols and functions related to variables and their relationships in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

^[

-0.61

 bords

-0.60

 Hör

-0.59

 Sprung

-0.57

 hàng

-0.57

Puss

-0.56

 DriverManager

-0.55

toko

-0.55

opor

-0.55

DriverManager

-0.54

POSITIVE LOGITS

phi

1.81

phi

1.52

Phi

1.46

Phi

1.44

psi

1.38

PHI

1.29

ϕ

1.25

Psi

1.25

varphi

1.22

Psi

1.21

Activations Density 0.133%

mathematical symbols and functions related to variables and their relationships in equations

No Comments

No Known Activations