INDEX

Explanations

repeated numerical sequences or structured data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

tvguidetime

-1.05

InjectAttribute

-0.98

+#+#

-0.93

IsContent

-0.88

onViewCreated

-0.88

 مشين

-0.86

 سكانية

-0.85

WriteTagHelper

-0.84

 defaultstate

-0.84

 createContext

-0.83

POSITIVE LOGITS

 perfect

0.50

0.49

 nearly

0.49

nu

0.44

ging

0.43

hal

0.42

 ente

0.42

 Perfect

0.42

par

0.42

at

0.41

Activations Density 0.023%

repeated numerical sequences or structured data points

No Comments

No Known Activations

repeated numerical sequences or structured data points

No Comments

No Known Activations