INDEX

Explanations

sections of text with relevant numerical data or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Hochspringen

-0.64

SequentialGroup

-0.58

 thous

-0.58

szt

-0.56

Şi

-0.55

 generalised

-0.54

WriteTagHelper

-0.54

ectoria

-0.54

 Stande

-0.53

yship

-0.53

POSITIVE LOGITS

rupulous

0.53

verwijspagina

0.53

 aDecoder

0.52

kháu

0.52

vidla

0.51

:");

0.51

oplayer

0.50

 recherchez

0.50

dinga

0.50

RTGC

0.50

Activations Density 0.017%

sections of text with relevant numerical data or symbols

No Comments

No Known Activations