INDEX

Explanations

terms related to public entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

rungsseite

-0.92

InjectAttribute

-0.86

ValueStyle

-0.85

 littéraire

-0.80

NameInMap

-0.80

RunWith

-0.78

KZ

-0.78

 resultCode

-0.73

 Lennox

-0.72

MCA

-0.71

POSITIVE LOGITS

 Public

1.33

Public

1.23

 PUBLIC

1.20

PUBLIC

1.16

 public

1.13

public

1.06

ublic

0.98

UBLIC

0.96

blic

0.94

 publik

0.93

Activations Density 0.066%

terms related to public entities or organizations

No Comments

No Known Activations