INDEX

Explanations

code-related terms and concepts in programming, especially those related to functions, debugging, and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ſtate

-0.88

 myſelf

-0.85

Efq

-0.84

 itſelf

-0.82

 Reſ

-0.81

 raiſ

-0.80

 faſt

-0.80

!*\

-0.79

 pleaſure

-0.79

 Diſ

-0.78

POSITIVE LOGITS

CrossRef

0.60

(!__

0.51

makeConstraints

0.49

SpringRunner

0.47

ⓧ

0.44

že

0.44

mit

0.44

Pur

0.43

 Obrador

0.40

 deepest

0.40

Activations Density 0.344%

code-related terms and concepts in programming, especially those related to functions, debugging, and error handling

No Comments

No Known Activations