INDEX

Explanations

terms related to statistical analysis and thresholds in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 CreateTagHelper

-0.85

 myſelf

-0.72

ViewImports

-0.69

SequentialGroup

-0.65

 للمعارف

-0.64

OOTDTY

-0.64

 Majefty

-0.61

 Wiktionnaire

-0.61

 ſhe

-0.59

Efq

-0.59

POSITIVE LOGITS

 subset

0.50

duy

0.46

 particularly

0.46

цездатний

0.45

 really

0.44

 nhất

0.44

限

0.44

才

0.43

 OnEnable

0.43

真正

0.43

Activations Density 0.830%

terms related to statistical analysis and thresholds in data

No Comments

No Known Activations