INDEX

Explanations

uses of the word "can" 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

WriteTagHelper

-0.97

rrggbb

-0.82

 CURIAM

-0.81

ThroughAttribute

-0.80

InjectAttribute

-0.80

Personensuche

-0.79

Попис

-0.76

dafx

-0.75

IUrlHelper

-0.72

writeFieldEnd

-0.69

POSITIVE LOGITS

 easily

1.16

 sometimes

0.90

 potentially

0.86

 also

0.86

be

0.83

 facilmente

0.76

 indeed

0.73

 fácilmente

0.72

 facilement

0.72

 still

0.70

Activations Density 0.258%

uses of the word "can" in various contexts

No Comments

No Known Activations