INDEX

Explanations

specific locations or points referenced in scientific measurements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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>

-0.53

sub

-0.45

me

-0.44

➟

-0.41

エ

-0.41

 stor

-0.41

 pair

-0.41

Sub

-0.41

par

-0.41

Me

-0.40

POSITIVE LOGITS

 pinulongan

0.99

saraba

0.91

mybatisplus

0.88

 defaultstate

0.88

IUrlHelper

0.86

 resourceCulture

0.81

oredCriteria

0.79

LEncoder

0.78

 ſeveral

0.77

 typelib

0.77

Activations Density 0.993%

specific locations or points referenced in scientific measurements or observations

No Comments

No Known Activations