INDEX

Explanations

the prefix "sp" indicating specific terms or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

actionMode

-0.71

úgó

-0.68

 myſelf

-0.65

 BoxFit

-0.65

seamnă

-0.64

 Roskov

-0.63

 physics

-0.63

Efq

-0.60

urization

-0.60

 Tahiti

-0.60

POSITIVE LOGITS

sp

0.68

principalTable

0.62

Cer

0.61

kab

0.60

stub

0.58

бель

0.58

jang

0.56

Pav

0.54

Bae

0.54

Activations Density 0.058%

the prefix "sp" indicating specific terms or phrases

No Comments

No Known Activations