INDEX

Explanations

references to personal experiences and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GOTREF

-0.83

 defaultstate

-0.83

MergeFrom

-0.74

CloseOperation

-0.70

AllowUser

-0.69

 kasarigan

-0.69

зулта

-0.66

Tikang

-0.63

 CURIAM

-0.63

DeleteBehavior

-0.62

POSITIVE LOGITS

 experienced

1.04

experienced

0.89

 Experienced

0.82

 lived

0.79

 visited

0.78

 heard

0.72

 experimentado

0.72

 tasted

0.71

 EXPERI

0.70

Experienced

0.70

Activations Density 0.330%

references to personal experiences and opinions

No Comments

No Known Activations