INDEX

Explanations

elements or objects in programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

บัติ

-0.67

gins

-0.60

on

-0.57

<em>

-0.57

oda

-0.57

-0.56

-0.55

-0.54

POSITIVE LOGITS

 newArray

1.03

unknownFields

1.00

[].

0.95

 arrayOf

0.94

 autorytatywna

0.92

 שוליים

0.91

 للمعارف

0.91

 pinulongan

0.90

 Arhi

0.90

.[/

0.89

Activations Density 0.053%

elements or objects in programming syntax

No Comments

No Known Activations