INDEX

Explanations

references to listings or categorizations related to objects or items, particularly in formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

EDEFAULT

-0.92

*/;

-0.84

]")]

-0.81

 ***/

-0.81

 neceff

-0.80

Efq

-0.79

 myſelf

-0.77

$_"

-0.76

$.

-0.76

 Monfieur

-0.76

POSITIVE LOGITS

 Make

0.61

ChildScrollView

0.60

Top

0.60

Theme

0.58

Listing

0.56

Make

0.53

Total

0.53

 Total

0.52

Top

0.52

0.49

Activations Density 0.119%

references to listings or categorizations related to objects or items, particularly in formal contexts

No Comments

No Known Activations