INDEX

Explanations

variables and functions related to mathematical equations and expressions in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ModelSerializer

-0.57

imágenes

-0.53

 —,

-0.51

permum

-0.49

—

-0.48

cerne

-0.46

()])

-0.46

{})

-0.45

})).

-0.45

ButterKnife

-0.45

POSITIVE LOGITS

_{

1.23

_{\

0.96

_{

0.91

_{+

0.80

<sub>

0.74

_{\

0.74

_{{\

0.73

_{-\

0.73

0.71

^{+}\

0.70

Activations Density 2.562%

variables and functions related to mathematical equations and expressions in a scientific context

No Comments

No Known Activations