INDEX

Explanations

references to scientific journals or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

migrationBuilder

-0.82

DockStyle

-0.77

yntaxException

-0.66

ContentAsync

-0.66

 neceffary

-0.62

MessageTagHelper

-0.61

PerformLayout

-0.60

PRNewswire

-0.59

ArgumentParser

-0.59

isome

-0.59

POSITIVE LOGITS

ستار

0.54

्य

0.49

υμα

0.48

rebbe

0.48

 consegu

0.47

PullParser

0.45

htä

0.44

是他

0.44

 goma

0.44

 tchèque

0.43

Activations Density 0.075%

references to scientific journals or publications

No Comments

No Known Activations