INDEX

Explanations

terms related to limitations or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 étoit

-0.97

 Monfieur

-0.93

 polaire

-0.92

 auroit

-0.90

mybatisplus

-0.86

 Theſe

-0.86

 Majefty

-0.84

 Diſ

-0.84

 photolibrary

-0.84

 ſtate

-0.83

POSITIVE LOGITS

 restricted

1.02

restricted

0.86

 restrict

0.86

 Restricted

0.85

Restricted

0.75

 gained

0.64

 restricting

0.62

 basic

0.59

es

0.58

de

0.57

Activations Density 0.116%

terms related to limitations or constraints

No Comments

No Known Activations