INDEX

Explanations

references to "short" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/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.36.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

Hentet

-0.60

ResumeLayout

-0.59

QMetaType

-0.56

Bronnen

-0.49

 EconPapers

-0.48

RTHOOK

-0.48

Бахар

-0.47

PyExc

-0.47

 незавершена

-0.46

⟬

-0.45

POSITIVE LOGITS

term

0.75

 SHORT

0.72

Term

0.71

lived

0.70

 Short

0.69

Short

0.69

 term

0.68

coming

0.67

sighted

0.66

 circu

0.66

Activations Density 0.119%

references to "short" and related terms

No Comments

No Known Activations