INDEX

Explanations

specific mechanical properties and alignments in engineering contexts

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

associated with "align" or "alignment"

np_acts-logits-general · gemini-2.0-flash

aligning words with others

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 demurrer

-0.55

 intensification

-0.52

şiv

-0.49

 filtration

-0.46

OPA

-0.45

Exponent

-0.45

 flamma

-0.45

 prostu

-0.44

eski

-0.44

AndEndTag

-0.43

POSITIVE LOGITS

 alignment

1.42

 Alignment

1.33

 aligning

1.24

 ALIGN

1.24

 align

1.23

alignment

1.20

 Align

1.20

Alignment

1.12

ALIGN

1.12

 aligned

1.11

Activations Density 0.394%

specific mechanical properties and alignments in engineering contexts

associated with "align" or "alignment"

aligning words with others

No Comments

No Known Activations