INDEX

Explanations

instances of the word "admit" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 calendriers

-0.52

 Lady

-0.48

 Verse

-0.46

 Kura

-0.45

 Sheldon

-0.44

 lady

-0.44

 Stru

-0.44

 folklor

-0.42

StringCopy

-0.42

 LADY

-0.42

POSITIVE LOGITS

 admit

3.75

 admitting

3.36

 admitted

3.31

 admits

3.27

 Admit

3.20

 admission

2.95

 Admission

2.61

Admission

2.52

admission

2.41

 admissions

2.39

Activations Density 0.082%

instances of the word "admit" or its variations

No Comments

No Known Activations