INDEX

Explanations

computer programming syntax and error messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

urangi

-0.51

isinstance

-0.48

 AppCompatTheme

-0.48

èdia

-0.43

 parlé

-0.41

osexuality

-0.41

 liberating

-0.41

 wystarczy

-0.41

 amiable

-0.41

 nawr

-0.40

POSITIVE LOGITS

 incorrect

1.43

 invalid

1.41

 wrong

1.37

 failed

1.31

invalid

1.29

 missing

1.28

 incorrectly

1.27

 unavailable

1.19

incorrect

1.17

Invalid

1.15

Activations Density 0.558%

computer programming syntax and error messages

No Comments

No Known Activations