INDEX

Explanations

phrases that indicate intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 cref

-0.79

сылкі

-0.77

stdc

-0.75

Билгалдахарш

-0.69

enosine

-0.63

ագրություններ

-0.63

DebuggerNonUser

-0.63

 تانيه

-0.63

endphp

-0.62

 linkovi

-0.62

POSITIVE LOGITS

envolvimento

0.61

chluss

0.58

 people

0.56

AsUp

0.56

 simply

0.54

czaj

0.54

oporosis

0.53

dshaw

0.53

 Vrbo

0.53

Activations Density 0.319%

phrases that indicate intention or purpose

No Comments

No Known Activations