INDEX

Explanations

references to various types of "baskets" and "chains"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

érios

-0.48

aim

-0.47

 للتو

-0.46

CDCl

-0.46

ked

-0.46

íma

-0.45

nuk

-0.45

σ

-0.45

mology

-0.45

 call

-0.44

POSITIVE LOGITS

 chains

1.00

 MainAxisSize

0.95

 itſelf

0.92

 fubject

0.91

 Jefus

0.91

 leaſt

0.90

 myſelf

0.89

 purpoſe

0.89

 Chains

0.88

 houſe

0.88

Activations Density 0.086%

references to various types of "baskets" and "chains"

No Comments

No Known Activations