INDEX

Explanations

phrases related to immersion or deep involvement in activities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

DoubleQuotes

-0.66

PreferredItem

-0.61

skjaer

-0.60

}();

-0.60

 jsPsych

-0.60

).</

-0.59

httphttps

-0.58

ativement

-0.58

[]:

-0.58

 AssemblyTitle

-0.58

POSITIVE LOGITS

 immersed

0.72

 into

0.72

 immerse

0.70

in

0.58

 Into

0.57

 immers

0.57

ADVERTISEMENT

0.55

lost

0.54

LOST

0.54

 lost

0.54

Activations Density 0.226%

phrases related to immersion or deep involvement in activities or experiences

No Comments

No Known Activations