INDEX

Explanations

occurrences of the abbreviation "s" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 تضيفلها

-0.74

 مرئيه

-0.72

原始内容存档于

-0.72

 pleaſure

-0.70

 Normdatei

-0.70

 cauſe

-0.68

eſt

-0.64

Sucesor

-0.64

 ſee

-0.63

 iſt

-0.62

POSITIVE LOGITS

XmlEnum

0.69

WriteTagHelper

0.67

0.65

InitVars

0.54

ként

0.53

ів

0.53

+#+#

0.51

es

0.51

 culoare

0.51

 obicei

0.50

Activations Density 0.159%

occurrences of the abbreviation "s" in various contexts

No Comments

No Known Activations