INDEX

Explanations

references to outcomes or results in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

__(/*!

-0.53

loride

-0.41

 acte

-0.38

antd

-0.38

clearAll

-0.38

 hadas

-0.38

__*/

-0.37

 понимать

-0.37

 useCallback

-0.37

 nonUne

-0.36

POSITIVE LOGITS

IntoConstraints

0.87

ui

0.56

StoryboardSegue

0.54

OptionsMenu

0.49

SceneManagement

0.49

 ModelAndView

0.48

 ObjectParameter

0.47

 onCreateView

0.46

flashdata

0.46

ModelAndView

0.45

Activations Density 0.000%

references to outcomes or results in a technical context

No Comments

No Known Activations

references to outcomes or results in a technical context

No Comments

No Known Activations