INDEX

Explanations

references to titles and character dynamics within narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Jefus

-0.90

 myſelf

-0.88

iffion

-0.84

IntoConstraints

-0.84

 newName

-0.84

ſelf

-0.83

 themſelves

-0.82

 purpoſe

-0.81

Amicalement

-0.81

 fhort

-0.80

POSITIVE LOGITS

ip

0.54

0.52

his

0.52

MathML

0.51

 character

0.51

 interpretar

0.50

0.49

解釈

0.49

 original

0.49

Character

0.48

Activations Density 0.293%

references to titles and character dynamics within narratives

No Comments

No Known Activations