INDEX

Explanations

terms related to excavation or searching for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Lari

-0.70

SuppressLint

-0.70

 disambiguazione

-0.68

saraba

-0.67

antMatchers

-0.67

Datuak

-0.66

 Kendall

-0.66

 SwiftUI

-0.66

Controllers

-0.64

 jurídico

-0.64

POSITIVE LOGITS

Dig

2.09

dig

2.05

Dig

2.04

 digging

1.92

dug

1.88

DIG

1.74

 digs

1.68

 digger

1.66

dig

1.65

Dug

1.50

Activations Density 0.113%

terms related to excavation or searching for information

No Comments

No Known Activations