INDEX

Explanations

references to mathematical bounds and limitations in relation to functions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 newBuilder

-0.59

Demografie

-0.58

 ExecuteAsync

-0.57

 onCreateView

-0.56

emang

-0.55

MessageDigest

-0.53

 ComVisible

-0.53

 siglas

-0.52

ready

-0.52

 görüntüsü

-0.52

POSITIVE LOGITS

 limitation

1.73

 limits

1.71

 limit

1.71

 limitations

1.68

 Limits

1.53

 limiting

1.53

limit

1.52

 Limit

1.51

 Limitation

1.50

 Limitations

1.47

Activations Density 0.566%

references to mathematical bounds and limitations in relation to functions or conditions

No Comments

No Known Activations