INDEX

Explanations

mathematical expressions related to directed graphs and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

<eos>

-0.48

↵↵

-0.45

zo

-0.43

 applications

-0.42

-0.41

 appeals

-0.41

 dare

-0.41

zo

-0.41

sqrt

-0.40

POSITIVE LOGITS

 ProtoMessage

0.97

 CreateTagHelper

0.97

HandlerContext

0.94

 مشين

0.92

 MainAxisSize

0.91

UnusedPrivate

0.90

principalColumn

0.88

BagConstraints

0.86

EndContext

0.85

addGap

0.81

Activations Density 1.373%

mathematical expressions related to directed graphs and their properties

No Comments

No Known Activations