INDEX

Explanations

statements reflecting past experiences and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 /\.(

-0.61

+#+#

-0.57

mandu

-0.56

enumi

-0.56

 Agus

-0.55

 prossimo

-0.55

endphp

-0.55

/***/

-0.53

 springfox

-0.53

fsch

-0.52

POSITIVE LOGITS

 sempat

0.81

 Initially

0.72

Was

0.71

 initially

0.71

MemoryWarning

0.71

 earlier

0.70

Initially

0.70

 previously

0.70

 originally

0.69

 Previously

0.68

Activations Density 0.253%

statements reflecting past experiences and conditions

No Comments

No Known Activations