INDEX

Explanations

phrases indicating the presence or quantity of items or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 متعلقه

-0.88

 themſelves

-0.87

RegressionTest

-0.85

RenderAtEndOf

-0.84

AddTagHelper

-0.82

 <=",

-0.82

 pleaſure

-0.81

UnusedPrivate

-0.81

 houſe

-0.79

 Jefus

-0.78

POSITIVE LOGITS

 many

0.85

 lots

0.83

 several

0.82

 numerous

0.77

0.73

 some

0.71

 plenty

0.70

 lauter

0.68

 elements

0.67

 both

0.65

Activations Density 0.400%

phrases indicating the presence or quantity of items or components

No Comments

No Known Activations