INDEX

Explanations

programming-related keywords and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 snippetHide

-0.66

+#+

-0.44

protoimpl

-0.43

 ब्रेकडाउन

-0.41

AndEndTag

-0.41

 Numerade

-0.39

nezeu

-0.38

개

-0.38

 ever

-0.38

#+#

-0.38

POSITIVE LOGITS

featureID

0.59

 Inſ

0.55

Enllaços

0.51

writeFieldEnd

0.48

 ſtre

0.47

tangentMode

0.47

 Reſ

0.47

 ſtate

0.46

 fieldNum

0.45

setViewportView

0.45

Activations Density 0.216%

programming-related keywords and function definitions

No Comments

No Known Activations