INDEX

Explanations

references to processes or events related to legal actions or document handling

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Jefus

-0.87

σθαι

-0.81

 houſe

-0.79

 Houſe

-0.79

 Diſ

-0.78

 Theſe

-0.78

 myſelf

-0.77

 tranſ

-0.77

 Chriftian

-0.77

 pleaſure

-0.77

POSITIVE LOGITS

AutoScaleMode

0.49

ie

0.47

to

0.45

].

0.44

 mxArray

0.43

sizeCache

0.43

Whilst

0.43

Viited

0.42

is

0.41

libft

0.41

Activations Density 0.459%

references to processes or events related to legal actions or document handling

No Known Activations