INDEX

Explanations

terms related to navigation and navigational tools

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

 &___

-0.78

RTHOOK

-0.68

MeasureSpec

-0.64

Asu

-0.62

 isolato

-0.62

 cser

-0.62

:+:

-0.62

 isolado

-0.61

 NgModule

-0.60

########.

-0.58

POSITIVE LOGITS

 navigation

1.66

 navig

1.58

nav

1.58

 navigate

1.54

 Navigation

1.47

navigate

1.44

 Navig

1.44

nav

1.43

Navigate

1.40

navig

1.40

Activations Density 0.096%

terms related to navigation and navigational tools

No Comments

No Known Activations