INDEX

Explanations

words related to possibilities and potential outcomes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 StatelessWidget

-0.91

PerformLayout

-0.82

 AspNetCore

-0.80

 tobacco

-0.80

 Reyna

-0.80

 Schna

-0.78

 StatefulWidget

-0.77

aarrggbb

-0.77

ed

-0.77

Yn

-0.77

POSITIVE LOGITS

 possible

2.00

 POSSIBLE

1.88

 Possible

1.87

Possible

1.85

possible

1.76

POSSIBLE

1.73

 posible

1.51

 possibili

1.51

 possib

1.50

 possibles

1.48

Activations Density 0.095%

words related to possibilities and potential outcomes

No Comments

No Known Activations