INDEX

Explanations

elements related to user interactions and comments in a web context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

TargetException

-0.84

+#+#

-0.80

 propOrder

-0.79

WriteTagHelper

-0.78

HtmlAttribute

-0.77

 kasarigan

-0.76

MemoryWarning

-0.75

 mergeFrom

-0.74

featureID

-0.70

 ModelExpression

-0.69

POSITIVE LOGITS

 options

0.52

 Options

0.49

 rest

0.46

 isotope

0.43

 kiin

0.43

bürger

0.42

 утро

0.42

korn

0.42

 Morel

0.42

 Ibis

0.41

Activations Density 0.429%

elements related to user interactions and comments in a web context

No Comments

No Known Activations