INDEX

Explanations

requests and inquiries for permissions or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 purpoſe

-0.69

 houſe

-0.68

дента

-0.68

 pleaſure

-0.63

 fubject

-0.62

 themſelves

-0.59

 nuclei

-0.59

 ſen

-0.59

 ſtate

-0.58

ſelf

-0.58

POSITIVE LOGITS

 request

0.77

 متعلقه

0.75

 Request

0.75

 requested

0.72

 requests

0.71

 Requests

0.69

req

0.67

 requesting

0.65

 gritos

0.64

 REQUEST

0.64

Activations Density 0.176%

requests and inquiries for permissions or information

No Comments

No Known Activations