INDEX

Explanations

expressions of opinion and reasoning

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

)_/¯

-0.57

 Normdatei

-0.56

__":

-0.56

✨:

-0.56

ientôt

-0.56

elemField

-0.56

setts

-0.56

GPR

-0.56

KURZBESCHREIBUNG

-0.55

usercontent

-0.54

POSITIVE LOGITS

 emphasise

0.55

 realise

0.54

BeginContext

0.53

 hindsight

0.52

 realises

0.52

MockBean

0.51

 realised

0.50

ISATION

0.49

 realising

0.49

Activations Density 0.129%

expressions of opinion and reasoning

No Comments

No Known Activations