INDEX

Explanations

code elements related to data handling and processing results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 архивлан

-0.61

elsif

-0.59

}`).

-0.53

ureusement

-0.50

dientemente

-0.50

:✨

-0.50

Whatever

-0.49

Gön

-0.48

Externí

-0.48

 nemlig

-0.47

POSITIVE LOGITS

,'\

0.83

,"\

0.81

RenderAtEndOf

0.77

StructEnd

0.63

","\

0.63

μάτων

0.62

UnsafeEnabled

0.60

 pprint

0.58

 "---

0.57

 Viter

0.56

Activations Density 0.072%

code elements related to data handling and processing results

No Comments

No Known Activations