INDEX

Explanations

phrases relating to limitations, restrictions, and liabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 onCreateView

-0.70

 nakalista

-0.63

gebob

-0.59

Salta

-0.59

SequentialGroup

-0.58

Demografie

-0.57

emang

-0.56

 saja

-0.56

RegistryLite

-0.56

idopsis

-0.56

POSITIVE LOGITS

 limitations

1.86

 limitation

1.81

 limits

1.78

 limit

1.70

 limiting

1.64

 Limitations

1.58

 Limitation

1.57

 limited

1.54

 Limits

1.52

 Limit

1.52

Activations Density 0.321%

phrases relating to limitations, restrictions, and liabilities

No Comments

No Known Activations