INDEX

Explanations

references to beams in various contexts

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

StoryboardSegue

-0.84

 ControllerBase

-0.78

AccessorTable

-0.76

WebServlet

-0.75

uidado

-0.73

jspb

-0.71

 fédéral

-0.70

 raisonnable

-0.70

RenderAtEndOf

-0.70

IVEREF

-0.68

POSITIVE LOGITS

tv

0.83

 personal

0.83

 secondary

0.59

Shared

0.58

 connecting

0.57

personal

0.54

 beam

0.54

 shared

0.51

 persoonlijke

0.49

tk

0.49

Activations Density 0.159%

references to beams in various contexts

No Comments

No Known Activations