INDEX

Explanations

functions and methods related to overriding in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

fon

-0.74

</i>

-0.72

res

-0.69

</h4>

-0.67

Frankie

-0.67

</u>

-0.66

 Plas

-0.65

</h2>

-0.63

\\

-0.60

BM

-0.60

POSITIVE LOGITS

override

1.19

 overrides

0.92

 override

0.92

Personendaten

0.86

 Overrides

0.85

 myſelf

0.83

 ""],

0.81

OrNil

0.81

 quelcon

0.81

 Keim

0.80

Activations Density 0.105%

functions and methods related to overriding in programming contexts

No Comments

No Known Activations