INDEX

Explanations

terms related to visibility and sensitivity

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

 palindrome

-0.78

 dolomite

-0.77

ագրություններ

-0.77

 فريبيس

-0.76

 jsPsych

-0.75

 Buckle

-0.73

UpInside

-0.73

 beren

-0.72

 idéia

-0.71

 étoient

-0.71

POSITIVE LOGITS

Mir

1.20

mir

1.16

Mir

1.10

MIR

0.90

mir

0.89

inv

0.87

 invasion

0.87

MIR

0.77

 pred

0.77

invasion

0.76

Activations Density 0.078%

terms related to visibility and sensitivity

No Comments

No Known Activations