INDEX

Explanations

occurrences of input/output terminology in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 morire

-0.98

 secoli

-0.82

CURLOPT

-0.78

 Berikut

-0.78

 automatiques

-0.78

 exacte

-0.77

@[+][

-0.76

 animés

-0.76

 Wale

-0.75

 gravure

-0.74

POSITIVE LOGITS

 input

1.57

 INPUT

1.56

 Input

1.52

 inputs

1.46

 Inputs

1.40

Input

1.39

INPUT

1.37

input

1.30

setInput

1.28

 输入

1.24

Activations Density 0.085%

occurrences of input/output terminology in technical contexts

No Comments

No Known Activations