INDEX

Explanations

references to organizations, locations, or individuals associated with various events or contexts

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

وصلات

-0.55

 règne

-0.51

letic

-0.50

(".")

-0.49

umin

-0.49

 provoke

-0.49

skine

-0.49

ardan

-0.49

[^

-0.48

poque

-0.48

POSITIVE LOGITS

setVerticalGroup

0.68

 locally

0.67

awaiter

0.66

Locally

0.65

 Locally

0.63

 local

0.62

AccessorTable

0.61

 تضيفلها

0.58

GraphicsUnit

0.56

esez

0.56

Activations Density 0.378%

references to organizations, locations, or individuals associated with various events or contexts

No Comments

No Known Activations