INDEX

Explanations

phrases that indicate suitability or compatibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Autoritní

-0.79

 consol

-0.79

 albedo

-0.77

dellín

-0.75

 Halley

-0.74

queurs

-0.74

 Moons

-0.73

updateUI

-0.72

quirrel

-0.72

 Dumont

-0.72

POSITIVE LOGITS

fit

2.70

fit

2.67

Fit

2.48

Fit

2.43

FIT

2.32

 fits

2.31

 Fits

2.17

fits

2.11

Fits

2.09

FIT

2.08

Activations Density 0.051%

phrases that indicate suitability or compatibility

No Comments

No Known Activations