INDEX

Explanations

preferences and choices regarding various options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ſever

-0.62

 itſelf

-0.61

 gonz

-0.57

 pleaſure

-0.57

AISSEE

-0.55

 canst

-0.54

 rasc

-0.53

IRIS

-0.53

 greateſt

-0.53

tagHelper

-0.53

POSITIVE LOGITS

 prefer

1.48

 prefers

1.33

 Prefer

1.33

prefer

1.30

 preferred

1.29

 preferring

1.29

Prefer

1.27

 preference

1.18

preferred

1.16

Preferred

1.09

Activations Density 0.226%

preferences and choices regarding various options

No Comments

No Known Activations