INDEX

Explanations

references to locations or states of being in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

hung

-0.49

[*]

-0.45

adalajara

-0.45

 Kunt

-0.44

/*

-0.44

memoized

-0.43

uebe

-0.43

tip

-0.42

ggere

-0.42

overe

-0.42

POSITIVE LOGITS

 sich

1.44

 się

1.24

 zich

1.16

 themselves

1.05

 himself

1.04

 yourself

0.99

 yourselves

0.98

 itself

0.98

 herself

0.97

themselves

0.96

Activations Density 0.031%

references to locations or states of being in various contexts

No Comments

No Known Activations