INDEX

Explanations

references to byte arrays and data structures involving byte manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

(!__

-0.86

rungsseite

-0.84

 okuyayım

-0.79

GEBURTSDATUM

-0.79

 '\\;'

-0.77

SBATCH

-0.75

BagConstraints

-0.73

LEGGI

-0.72

awtextra

-0.69

 وتسجيلات

-0.69

POSITIVE LOGITS

 bytes

1.10

 byte

1.08

bytes

1.07

Bytes

1.05

 Byte

1.05

Byte

1.02

 Bytes

0.99

BYTES

0.99

 BYTE

0.95

byte

0.92

Activations Density 0.147%

references to byte arrays and data structures involving byte manipulation

No Comments

No Known Activations