INDEX

Explanations

phrases and terminology related to equivalence and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

unnitel

-0.71

endpush

-0.70

 jadx

-0.60

कर्ष

-0.60

 Dooley

-0.60

 Audiodateien

-0.60

dymyr

-0.58

 MNRAS

-0.58

siella

-0.58

 Hurley

-0.56

POSITIVE LOGITS

 equivalent

3.38

equivalent

3.05

 Equivalent

2.95

Equivalent

2.82

 equivalents

2.78

 equivalente

2.57

 equival

2.29

 équi

2.27

 equivalence

2.22

equi

2.06

Activations Density 0.111%

phrases and terminology related to equivalence and comparisons

No Comments

No Known Activations