INDEX

Explanations

text related to technical details and problem-solving scenarios

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

 lama

-0.41

licação

-0.40

AddTagHelper

-0.40

oznam

-0.40

்கள

-0.39

 malu

-0.39

置く

-0.38

 lượt

-0.37

 widok

-0.37

 actuels

-0.37

POSITIVE LOGITS

RegressionTest

0.57

 supposed

0.51

supposed

0.47

 Audiodateien

0.45

 quæ

0.44

 supuestamente

0.43

loroethene

0.43

以為

0.43

 ✭✭

0.43

 bivolt

0.42

Activations Density 0.681%

text related to technical details and problem-solving scenarios

No Comments

No Known Activations