INDEX

Explanations

instances of the word "peak" and related phrases indicating maximum values or levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

.........

-0.66

 fact

-0.64

Kot

-0.58

 Jarvis

-0.56

lisle

-0.55

Kot

-0.55

MathML

-0.53

 miel

-0.53

POSITIVE LOGITS

 peak

1.65

 peaks

1.63

 Peak

1.55

 PEAK

1.54

Peak

1.49

 Peaks

1.47

peak

1.38

 peaking

1.34

 peaked

1.27

peaks

1.26

Activations Density 0.123%

instances of the word "peak" and related phrases indicating maximum values or levels

No Comments

No Known Activations