INDEX

Explanations

test-related terms and phrases in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 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

PerformLayout

-0.58

 الحره

-0.56

 ControllerBase

-0.48

 anthropologist

-0.48

 oprot

-0.44

 anthropology

-0.44

 anthropologists

-0.44

étoit

-0.43

DebuggerNonUser

-0.43

GOTREF

-0.43

POSITIVE LOGITS

 simple

0.49

non

0.47

mis

0.47

 explicit

0.45

 incorrect

0.44

 basic

0.43

Tikang

0.43

 multiple

0.43

 effort

0.43

 برانيه

0.43

Activations Density 0.284%

test-related terms and phrases in programming contexts

No Comments

No Known Activations