INDEX

Explanations

terms related to status or state indicators in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

]--;

-0.90

 Monfieur

-0.84

 userDao

-0.83

)}(\

-0.82

 greateſt

-0.79

ագրություններ

-0.78

 haja

-0.77

 leaſt

-0.77

 AppColors

-0.74

клопе

-0.73

POSITIVE LOGITS

 status

3.17

 Status

3.14

status

3.02

Status

3.02

 STATUS

2.94

STATUS

2.84

 statuses

2.61

 getStatus

2.48

getStatus

2.48

setStatus

2.21

Activations Density 0.061%

terms related to status or state indicators in programming contexts

No Comments

No Known Activations