INDEX

Explanations

topics related to reputation and image management

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

stdc

-0.66

IntoConstraints

-0.63

makeText

-0.62

WebControls

-0.55

 réunis

-0.53

 Convergence

-0.52

AsStream

-0.52

iastes

-0.52

 venons

-0.51

migrationBuilder

-0.51

POSITIVE LOGITS

 reputation

1.85

 image

1.61

 Reputation

1.46

 reputations

1.40

Reputation

1.32

 reput

1.29

image

1.28

 reputa

1.27

 réputation

1.24

 Image

1.21

Activations Density 0.334%

topics related to reputation and image management

No Comments

No Known Activations