INDEX

Explanations

references to "post" in various contexts, particularly in relation to events or conditions that follow a particular occurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 wireType

-0.46

Nearby

-0.45

CommandType

-0.44

#+#

-0.43

 crou

-0.42

rzej

-0.42

 vecin

-0.42

前に

-0.41

intur

-0.41

 CommandType

-0.41

POSITIVE LOGITS

tagHelperRunner

0.91

__":

0.72

----</

0.70

 RoutedEventArgs

0.69

 pandemic

0.68

post

0.67

 doInBackground

0.66

########.

0.64

)_/¯

0.64

bootstrapcdn

0.64

Activations Density 0.170%

references to "post" in various contexts, particularly in relation to events or conditions that follow a particular occurrence

No Comments

No Known Activations