INDEX

Explanations

references to memory management or memory components in programming or hardware contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 propOrder

-0.85

LayoutStyle

-0.78

Autoritní

-0.73

 autorytatywna

-0.66

 MessageBoxIcon

-0.65

Diwedd

-0.65

الدراسه

-0.64

 jadx

-0.63

GEBURTS

-0.61

WebServlet

-0.60

POSITIVE LOGITS

Shared

1.14

Mem

1.02

Mem

1.01

mem

0.97

Share

0.89

mem

0.84

shared

0.82

SHARED

0.80

share

0.77

SHARE

0.64

Activations Density 0.120%

references to memory management or memory components in programming or hardware contexts

No Comments

No Known Activations