INDEX

Explanations

explanations and clarifications about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Stardust

-0.60

Carlton

-0.56

 Crows

-0.52

 Normdatei

-0.52

 BIBSYS

-0.52

IBar

-0.51

jsonwebtoken

-0.51

Raven

-0.51

 Roost

-0.50

ragamo

-0.50

POSITIVE LOGITS

 explain

1.02

 explanation

0.93

 explaining

0.93

explain

0.93

 explains

0.92

 explained

0.91

 Explain

0.91

 explanations

0.90

 explicación

0.84

 explica

0.82

Activations Density 0.101%

explanations and clarifications about various subjects

No Comments

No Known Activations