INDEX

Explanations

discussions about trade-offs, pros and cons, and evaluations of worth or value

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Roskov

-0.63

ElementException

-0.61

 intptr

-0.57

awtextra

-0.56

TagHelpers

-0.54

TagHelper

-0.54

Personendaten

-0.53

ensement

-0.52

 ModelRenderer

-0.52

LEncoder

-0.52

POSITIVE LOGITS

 reward

0.66

 rewards

0.64

reward

0.60

 benefits

0.59

 Dafür

0.59

athione

0.58

ofür

0.58

 promise

0.57

 recompensa

0.56

 cser

0.56

Activations Density 0.303%

discussions about trade-offs, pros and cons, and evaluations of worth or value

No Comments

No Known Activations