INDEX

Explanations

terms related to pulses and their variations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Montero

-0.81

browserify

-0.79

mpg

-0.79

 Dany

-0.78

 Michaelis

-0.78

UTM

-0.76

CloseOperation

-0.74

 Kino

-0.74

SOT

-0.73

Indo

-0.73

POSITIVE LOGITS

 pulse

1.65

 pulses

1.52

 Pulse

1.49

pulse

1.42

Pulse

1.39

pul

1.26

PUL

1.15

PUL

1.14

Pul

1.09

pul

1.09

Activations Density 0.015%

terms related to pulses and their variations

No Comments

No Known Activations