INDEX

Explanations

references to popularity or well-known concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.68

ள்

-0.66

anstalt

-0.64

τ

-0.63

hemiah

-0.61

is

-0.59

-0.58

bindValue

-0.57

jooq

-0.57

 niega

-0.57

POSITIVE LOGITS

Efq

1.66

 myſelf

1.52

 pleaſure

1.51

 Theſe

1.50

 Jefus

1.48

 themſelves

1.46

 whoſe

1.45

 Monfieur

1.42

 iſt

1.39

 leſs

1.39

Activations Density 0.043%

references to popularity or well-known concepts

No Comments

No Known Activations