INDEX

Explanations

references to specific individuals or organizations in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 préc

-0.46

 fermée

-0.44

 dispozici

-0.43

 obuv

-0.43

 føl

-0.43

 artificiales

-0.42

 Eintritt

-0.41

 CreateTagHelper

-0.41

 eşofman

-0.41

harapkan

-0.41

POSITIVE LOGITS

der

0.95

Der

0.85

Der

0.85

Dar

0.81

Dar

0.81

DER

0.76

DER

0.74

dar

0.73

der

0.73

Дер

0.73

Activations Density 1.591%

references to specific individuals or organizations in academic contexts

No Comments

No Known Activations